US20040267397A1 - Optical metrology of structures formed on semiconductor wafer using machine learning systems - Google Patents
Optical metrology of structures formed on semiconductor wafer using machine learning systems Download PDFInfo
- Publication number
- US20040267397A1 US20040267397A1 US10/608,300 US60830003A US2004267397A1 US 20040267397 A1 US20040267397 A1 US 20040267397A1 US 60830003 A US60830003 A US 60830003A US 2004267397 A1 US2004267397 A1 US 2004267397A1
- Authority
- US
- United States
- Prior art keywords
- machine learning
- learning system
- diffraction
- diffraction signal
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L22/00—Testing or measuring during manufacture or treatment; Reliability measurements, i.e. testing of parts without further processing to modify the parts as such; Structural arrangements therefor
Definitions
- the present invention relates to metrology of structures formed on semiconductor wafers, and more particularly to metrology of structures formed on semiconductor wafers using machine learning systems.
- Optical metrology involves directing an incident beam at a structure, measuring the resulting diffracted beam, and analyzing the diffracted beam to determine a feature of the structure.
- optical metrology is typically used for quality assurance. For example, after fabricating a periodic grating in proximity to a semiconductor chip on a semiconductor wafer, an optical metrology system is used to determine the profile of the periodic grating. By determining the profile of the periodic grating, the quality of the fabrication process utilized to form the periodic grating, and by extension the semiconductor chip proximate the periodic grating, can be evaluated.
- One conventional optical metrology system uses a diffraction modeling technique, such as rigorous coupled wave analysis (RCWA), to analyze the diffracted beam. More particularly, in the diffraction modeling technique, a model diffraction signal is calculated based, in part, on solving Maxwell's equations. Calculating the model diffraction signal involves performing a large number of complex calculations, which can be time consuming and costly.
- RCWA rigorous coupled wave analysis
- a structure formed on a semiconductor wafer is examined by obtaining a first diffraction signal measured using a metrology device.
- a second diffraction signal is generated using a machine learning system, where the machine learning system receives as an input one or more parameters that characterize a profile of the structure to generate the second diffraction signal.
- the first and second diffraction signals are compared.
- a feature of the structure is determined based on the one or more parameters or the profile used by the machine learning system to generate the second diffraction signal.
- FIG. 1 depicts an exemplary optical metrology system
- FIGS. 2A-2E depict exemplary profiles
- FIG. 3 depicts an exemplary neural network
- FIG. 4 depicts an exemplary process of training a machine learning system
- FIG. 5 depicts an exemplary process of testing a machine learning system
- FIG. 6 depicts an exemplary process of determining a feature of a structure using a machine learning system
- FIG. 7 depicts an exemplary process of determining a feature of a structure using a machine learning system in a library-based process
- FIG. 8 depicts an exemplary system to determine a feature of a structure using a machine learning system in a library-based system
- FIG. 9 depicts an exemplary process of determining a feature of a structure using a machine learning system in a regression-based process
- FIG. 10 depicts an exemplary system to determine a feature of a structure using a machine learning system in a regression-based system.
- a metrology system 100 can be used to examine and analyze a structure.
- metrology system 100 can be used to determine a feature of a periodic grating 102 formed on wafer 104 .
- periodic grating 102 can be formed in test areas on wafer 104 , such as adjacent to a device formed on wafer 104 .
- periodic grating 102 can be formed in an area of the device that does not interfere with the operation of the device or along scribe lines on wafer 104 .
- metrology system 100 can include a metrology device with a source 106 and a detector 112 .
- Periodic grating 102 is illuminated by an incident beam 108 from source 106 .
- incident beam 108 is directed onto periodic grating 102 at an angle of incidence ⁇ i with respect to normal n of periodic grating 102 and an azimuth angle ⁇ (i.e., the angle between the plane of incidence beam 108 and the direction of the periodicity of periodic grating 102 ).
- Diffracted beam 110 leaves at an angle of ⁇ d with respect to normal ⁇ right arrow over (n) ⁇ and is received by detector 112 .
- Detector 112 converts the diffracted beam 110 into a measured diffraction signal, which can include reflectance, tan ( ⁇ ), cos ( ⁇ ), Fourier coefficients, and the like.
- Metrology system 100 also includes a processing module 114 configured to receive the measured diffraction signal and analyze the measured diffraction signal. As described below, a feature of periodic grating 102 can then be determined using a library-based process or a regression-based process. Additionally, other linear or non-linear profile extraction techniques are contemplated.
- the measured diffraction signal is compared to a library of diffraction signals. More specifically, each diffraction signal in the library is associated with a profile of the structure.
- each diffraction signal in the library is associated with a profile of the structure.
- the profile associated with the matching diffraction signal in the library is presumed to represent the actual profile of the structure.
- a feature of the structure can then be determined based on the profile associated with the matching diffraction signal.
- processing module 114 compares the measured diffraction signal to diffraction signals stored in a library 116 .
- Each diffraction signal in library 116 is associated with a profile.
- the profile associated with the matching diffraction signal in library 116 can be presumed to represent the actual profile of periodic grating 102 .
- the set of profiles stored in library 116 can be generated by characterizing a profile using a set of parameters, then varying the set of parameters to generate profiles of varying shapes and dimensions.
- the process of characterizing a profile using a set of parameters can be referred to as parameterizing.
- profile 200 can be characterized by parameters h1 and w1 that define its height and width, respectively.
- additional shapes and features of profile 200 can be characterized by increasing the number of parameters.
- profile 200 can be characterized by parameters h1, w1, and w2 that define its height, bottom width, and top width, respectively.
- the width of profile 200 can be referred to as the critical dimension (CD).
- parameter w1 and w2 can be described as defining the bottom CD and top CD, respectively, of profile 200 .
- various types of parameters can be used to characterize profile 200 , including angle of incident (AOI), pitch, n & k, hardware parameters (e.g., polarizer angle), and the like.
- the set of profiles stored in library 116 can be generated by varying the parameters that characterize the profile. For example, with reference to FIG. 2B, by varying parameters h1, w1, and w2, profiles of varying shapes and dimensions can be generated. Note that one, two, or all three parameters can be varied relative to one another.
- the parameters of the profile associated with a matching diffraction signal can be used to determine a feature of the structure being examined.
- a parameter of the profile corresponding to a bottom CD can be used to determine the bottom CD of the structure being examined.
- the number of profiles and corresponding diffraction signals in the set of profiles and diffraction signals stored in library 116 depends, in part, on the range over which the set of parameters and the increment at which the set of parameters are varied.
- the profiles and the diffraction signals stored in library 116 are generated prior to obtaining a measured diffraction signal from an actual structure.
- the range and increment (i.e., the range and resolution) used in generating library 116 can be selected based on familiarity with the fabrication process for a structure and what the range of variance is likely to be.
- the range and/or resolution of library 116 can also be selected based on empirical measures, such as measurements using atomic force microscopy (AFM), scanning electron microscopy (SEM), and the like.
- the measured diffraction signal is compared to a diffraction signal generated prior to the comparison (i.e., a trial diffraction signal) using a set of parameters (i.e., trial parameters) for a profile. If the measured diffraction signal and the trial diffraction signal do not match or when the difference of the measured diffraction signal and the trial diffraction signal is not within a preset or matching criterion, another trial diffraction signal is generated using another set of parameters for another profile, then the measured diffraction signal and the newly generated trial diffraction signal are compared.
- a diffraction signal generated prior to the comparison i.e., a trial diffraction signal
- trial parameters i.e., trial parameters
- the profile associated with the matching trial diffraction signal is presumed to represent the actual profile of the structure.
- the profile associated with the matching trail diffraction signal can then be used to determine a feature of the structure being examined.
- processing module 114 can generate a trial diffraction signal for a profile, and then compare the measured diffraction signal to the trial diffraction signal. As described above, if the measured diffraction signal and the trial diffraction signal do not match or when the difference of the measured diffraction signal the trial diffraction signals is not within a preset or matching criterion, then processing module 114 can iteratively generate another trial diffraction signal for another profile.
- the subsequently generated trial diffraction signal can be generated using an optimization algorithm, such as global optimization techniques, which includes simulated annealing, and local optimization techniques, which includes steepest descent algorithm.
- the trial diffraction signals and profiles can be stored in a library 116 (i.e., a dynamic library).
- the trial diffraction signals and profiles stored in library 116 can then be subsequently used in matching the measured diffraction signal.
- library 116 can be omitted from metrology system 100 .
- diffraction signals used in a library-based process and/or a regression-based process are generated using a machine learning system 118 employing a machine learning algorithm, such as back-propagation, radial basis function, support vector, kernel regression, and the like.
- a machine learning algorithm such as back-propagation, radial basis function, support vector, kernel regression, and the like.
- machine learning system 118 receives a profile as an input and generates a diffraction signal as an output.
- machine learning system 118 is depicted as a component of processing module 114 , it should be recognized that machine learning system 118 can be a separate module.
- the diffraction signals in library 116 can be generated in advance by machine learning system 118 .
- machine learning system 118 can be a separate module that is not connected to processing module 114 .
- machine learning system 118 is used as part of a regression-based process, machine learning system 118 is connected to processing module 114 even when machine learning system 118 is a separate module rather than a component of processing module 114 .
- the machine learning system is a neural network 300 using a back-propagation algorithm.
- Neural network 300 includes an input layer 302 , an output layer 304 , and a hidden layer 306 between input layer 302 and output layer 304 .
- Input layer 302 and hidden layer 306 are connected using links 308 .
- Hidden layer 306 and output layer 304 are connected using links 310 . It should be recognized, however, that neural network 300 can include any number of layers connected in various configurations.
- input layer 302 includes one or more input nodes 312 .
- an input node 312 in input layer 302 corresponds to a parameter of the profile that is inputted into neural network 300 .
- the number of input nodes 312 corresponds to the number of parameters used to characterize the profile. For example, if a profile is characterized using 2 parameters (e.g., top and bottom widths), input layer 302 includes 2 input nodes 312 , where a first input node 312 corresponds to a first parameter (e.g., a top width) and a second input node 312 corresponds to a second parameter (e.g., a bottom width).
- output layer 304 includes one or more output nodes 314 .
- each output node 314 is a linear function. It should be recognized, however, that each output node 314 can be various types of functions.
- an output node 314 in output layer 304 corresponds to a dimension of the diffraction signal that is outputted from neural network 300 .
- the number of output nodes 314 corresponds to the number of dimensions used to characterize the diffraction signal.
- output layer 304 includes 5 output nodes 314 , wherein a first output node 314 corresponds to a first dimension (e.g., a first wavelength), a second output node 314 corresponds to a second dimension (e.g., a second wavelength), etc.
- a first output node 314 corresponds to a first dimension (e.g., a first wavelength)
- a second output node 314 corresponds to a second dimension (e.g., a second wavelength)
- hidden layer 306 includes one or more hidden nodes 316 .
- each hidden node 316 is a sigmoidal transfer function or a radial basis function. It should be recognized, however, that each hidden node 316 can be various types of functions.
- the machine learning system Prior to using a machine learning system to generate a diffraction signal, the machine learning system is trained. With reference to FIG. 4, an exemplary process 400 is depicted for training a machine learning system.
- the machine learning system is trained using a set of training input data and a set of training output data, where an input data in the set of training input data has a corresponding output data in the set of training output data to form an input and an output data pair.
- the set of training input data is obtained.
- the training input data includes a set of profiles.
- a profile is characterized using a set of parameters.
- a range of profiles can be generated by varying one or more parameters that characterize a profile, either alone or in combination.
- An overall range of profiles to be generated is determined based on the expected range of variability in the actual profile of the structure to be examined, which is determined either empirically or through experience. For example, if the actual profile of the structure to be examined is expected to have a bottom width that can vary between x 1 and x 2 , then the overall range of profiles can be generated by varying the parameter corresponding to the bottom width between x 1 and x 2 .
- the set of profiles used to train the machine learning system is selected from the overall range of profiles to be generated. More particularly, the training data set is selected using a random sampling of the overall range of profiles. It should be recognized that various sampling techniques can be used to select the training data set, such as systematic sampling, a combination of random and systematic sampling, and the like.
- the overall range of profiles to be generated is divided into two or more partitions.
- a machine learning system is configured and trained for each of the partitions. For example, assume the overall range is divided into a first partition and a second partition. Thus, in this example, a first machine learning system is configured and trained for the first partition, and a second machine learning system is configured and trained for the second partition.
- One advantage of partitioning the overall range and using multiple machine learning systems is that parallel processing can be used (e.g., the two machine learning systems can be trained and used in parallel).
- Another advantage is that each of the machine learning systems may be more accurate as to their respective partitions than a single machine learning system for the overall range. More specifically, a single machine learning system trained for the overall range may be susceptible to a local minimum that may reduce the accuracy of the machine learning system.
- the partitions may be of equal sizes or of varying sizes.
- the sizes of the partitions can be determined based on the density of the data within the partitions. For example, a less dense partition may be larger than a more dense partition. It should be recognized that the number and size of the partitions can vary depending on the application.
- the set of training output data is obtained.
- the training output data includes a set of diffraction signals.
- a diffraction signal in the set of diffraction signals used as the training output data corresponds to a profile in the set of profiles used as the training input data.
- Each diffraction signal in the set of diffraction signals can be generated based on each profile in the set of profiles using a modeling technique, such as rigorous coupled wave analysis (RCWA), integral method, Fresnel method, finite analysis, modal analysis, and the like.
- RCWA rigorous coupled wave analysis
- each diffraction signal in the set of diffraction signals can be generated based on each profile in the set of profiles using an empirical technique, such as measuring a diffraction signal using a metrology device, such as an ellipsometer, reflectometer, atomic force microscope (AFM), scanning electron microscope (SEM), and the like.
- a metrology device such as an ellipsometer, reflectometer, atomic force microscope (AFM), scanning electron microscope (SEM), and the like.
- the set of diffraction signals is transformed using principal component analysis (PCA). More particularly, a diffraction signal can be characterized using a number of dimensions, such as a number of different wavelengths.
- PCA principal component analysis
- the diffraction signals are transformed into uncorrelated dimensions, and the space of the uncorrelated dimensions is smaller than the space of the original dimensions. After the machine learning system has been trained, the diffraction signals can be transformed back.
- the dimensions of the diffraction signals can be divided into two or more partitions.
- a machine learning system is configured and trained for each of the partitions. For example, assume the dimensions are divided into a first partition and a second partition. Thus, in this example, a first machine learning system is configured and trained for the first partition, and a second machine learning system is configured and trained for the second partition.
- partitioning the dimensions and using multiple machine learning systems is that parallel processing can be used (e.g., the two machine learning systems can be trained and used in parallel).
- Another advantage is that each of the machine learning systems may be more accurate as to their respective partitions than a single machine learning system.
- a diffraction signal is generated using the machine learning system.
- the generated diffraction signal is compared with the diffraction signal from the set of diffraction signals that corresponds to the profile.
- 406 and 408 are repeated with another profile from the set of profiles used as the training input data.
- the training process is terminated.
- training process 400 can include the use of an optimization technique, such as gradient descent, linear programming, quadratic programming, simulated annealing, Marquardt-Levenberg algorithm, and the like. Additionally, training process 400 can be performed as a batch process. For a more detailed description of a batch process, see “Neural Networks” by Simon Haykin, which has been cited above.
- training process 400 depicted in FIG. 4 illustrates a back-propagation algorithm.
- various training algorithms can be used, such as radial basis network, support vector, kernel regression, and the like.
- an exemplary process 500 is depicted for testing a machine learning system.
- the machine learning system can be tested to confirm that it has been properly trained. It should be recognized, however, that this testing process can be omitted in some applications.
- a set of testing input data is obtained.
- a set of testing output data is obtained.
- the testing input data includes a set of profiles, and the testing output data includes a set of diffraction signals.
- the set of testing input data and set of testing output data can be obtained using the same process and techniques described above during the training process.
- the set of testing input data and set of testing output data can be the same as or a subset of the training input data and training output data.
- the set of testing input data and set of testing out data can be different than the training input data and training output data.
- a diffraction signal is generated using the machine learning system.
- the generated diffraction signal is compared with the diffraction signal from the set of diffraction signals in the testing output data that corresponds to the profile.
- the machine learning system is re-trained.
- the training process can be adjusted. For example, the selection and number of the training input and output variables can be adjusted. Additionally, the machine learning system can be adjusted. For example, when the machine learning system is a neural network, as described above, the number of hidden nodes can be adjusted.
- the testing process is terminated.
- ERM empirical risk minimization
- the machine learning system can be used to generate diffraction signals for use in analyzing a structure formed on a semiconductor wafer. Again, it should be noted that the testing process can be omitted in some applications.
- an exemplary process 600 is depicted for using a machine learning system to examine a structure formed on a semiconductor wafer.
- a measured diffraction signal of the structure is obtained by using a metrology device.
- a generated diffraction signal is obtained using the machine learning system.
- the diffraction signals are compared.
- a feature of the structure is determined based on the comparison of the measured and generated diffraction signals.
- a profile corresponding to the generated diffraction signal is used as an input to the machine learning system to generate the generated diffraction signal.
- the profile is characterized by one or more parameters.
- an exemplary process 700 is depicted for using a machine learning system in a library-based process.
- a library of diffraction signals are generated using the machine learning system. More particularly, the library of diffraction signals is generated by inputting a range of profiles into the machine learning system.
- a measured diffraction signal is obtained using a metrology device, such as an ellipsometer, reflectometer, and the like.
- the measured diffraction signal is compared to the diffraction signals in the library of diffraction signals generated using the machine learning system.
- a feature of the structure is determined using the profile corresponding to the matching diffraction signal from the library of diffraction signals.
- an exemplary system 800 is depicted for using a machine learning system in a library-based system.
- library 116 is generated using machine learning system 118 .
- Library 116 is then used by processing module 114 to compare the diffraction signals in library 116 to measured diffraction signals obtained from a metrology device 802 , such as an ellipsometer, a reflectometer, and the like.
- a metrology device 802 such as an ellipsometer, a reflectometer, and the like.
- machine learning system 118 is depicted as a separate unit in FIG. 8, machine learning system 118 can be integrated as a component of processing module 114 .
- machine learning system 118 can be connected to processing module 114 to transmit library 116 to processing module 114 , such as through a network connection.
- library 116 can be stored on a portable storage medium and physically transported to processing module 114 .
- processing module 114 can be coupled to a semiconductor fabrication unit 804 that is configured to perform one or more fabrication steps. It should be recognized, however, that the metrology system can operate as a stand-alone system in addition to being integrated with semiconductor fabrication unit 804 .
- an exemplary process 900 is depicted for using a machine learning system in a regression-based process.
- a measured diffraction signal is obtained using a metrology device, such as an ellipsometer, reflectometer, atomic force microscope (AFM), scanning electron microscope (SEM),and the like.
- a generated diffraction signal is obtained using the machine learning system.
- the two diffraction signals are compared. When the two diffraction signals do not match within a predetermined matching criterion, 904 and 906 are repeated with another diffraction signal generated in 904 .
- This process is iterated until a match is found, meaning that the generated and measured diffraction signals match within the predetermined matching criterion.
- the profile corresponding to the matching diffraction signal is assumed to correspond to the actual profile of the structure being examined.
- the profile and the parameters that characterize the profile can be used to determine a feature of the structure.
- an exemplary system 1000 is depicted for using a machine learning system in a regression-based system.
- an optimizer 1002 receives the measured diffraction signal as an input from metrology device 802 .
- Optimizer 1002 receives the generated diffraction signal as an input from machine learning system 118 .
- Optimizer 1002 compares the generated and the measured diffraction signals. When the generated and measured diffraction signals do match, optimizer 1002 outputs the profile corresponding to the matching generated diffraction signal. When the generated and measured diffraction signals do not match within a predetermined matching criterion, optimizer 1002 outputs a signal to machine learning system 118 to generate another diffraction signal. This process is iterated until a match is found, meaning that the generated and measured diffraction signals match within the predetermined matching criterion.
- an optimization technique is used to reduce the number of iterations needed to arrive at a match. More particularly, the aim of an optimization problem is to find a best solution among several possible solutions, where the best solution can be quantified by associating a cost function. In other words, for a given problem under a given cost metric, the task is to find a solution with the least cost. Thus, in the present exemplary application, the task is to find the profile with a corresponding diffraction signal that produces the least cost (under a given cost metric) with respect to the given measured diffraction signal.
- optimization techniques which are broadly classified into two categories (i.e., global and local), are known and can be used, such as gradient descent, linear programming, quadratic programming, simulated annealing, Marquardt-Levenberg algorithm, and the like.
- global and local optimization techniques see “Numerical Recipes in C”, by William H. Press, Saul A. Teukolsky, William T. Vetterling and Brian P. Flannery, Second Edition, Cambridge, which is incorporated herein by reference.
- a library of diffraction signals can be generated as part of a regression-based process. More particularly, when a match has been made, meaning that the generated diffraction signal and the measured diffraction signal match within the matching criterion, a library of diffraction signals can be generated around the matching profile. Generally, the library of diffraction signals generated as part of the regression-based process is smaller than the library that is generated as part of the library-based process described above.
- the library of diffraction signals generated as part of a regression-based process and the library generated as part of a library-based process described above can be used in an interpolation process, where a solution is derived between two entries in the library.
- an interpolation process see U.S. patent application Ser. No. 10/075,904, titled PROFILE REFINEMENT FOR INTEGRATED CIRCUIT METROLOGY, filed on Feb. 12, 2002, which is incorporated herein by reference in its entirety.
- machine learning system 118 can be configured to operate with a non-optical metrology device, such as an atomic force microscope (AFM), scanning electron microscopes (SEM), and the like, or a combination of an optical and a non-optical metrology device.
- a non-optical metrology device such as an atomic force microscope (AFM), scanning electron microscopes (SEM), and the like
- machine learning system 118 can generate various types of diffraction signals corresponding to the type of metrology device used.
- the diffraction signal generated by machine learning system 118 is a SEM signal, such as two-dimensional images or SEM traces.
- the diffraction signal generated can include characteristic functions of the signal used by the metrology device.
- various order derivatives e.g., first order, second order . . . n th order derivatives
- Marquardt-Levenberg algorithm to optimize the training process.
Abstract
Description
- 1. Field of the Invention
- The present invention relates to metrology of structures formed on semiconductor wafers, and more particularly to metrology of structures formed on semiconductor wafers using machine learning systems.
- 2. Related Art
- Optical metrology involves directing an incident beam at a structure, measuring the resulting diffracted beam, and analyzing the diffracted beam to determine a feature of the structure. In semiconductor manufacturing, optical metrology is typically used for quality assurance. For example, after fabricating a periodic grating in proximity to a semiconductor chip on a semiconductor wafer, an optical metrology system is used to determine the profile of the periodic grating. By determining the profile of the periodic grating, the quality of the fabrication process utilized to form the periodic grating, and by extension the semiconductor chip proximate the periodic grating, can be evaluated.
- One conventional optical metrology system uses a diffraction modeling technique, such as rigorous coupled wave analysis (RCWA), to analyze the diffracted beam. More particularly, in the diffraction modeling technique, a model diffraction signal is calculated based, in part, on solving Maxwell's equations. Calculating the model diffraction signal involves performing a large number of complex calculations, which can be time consuming and costly.
- In one exemplary embodiment, a structure formed on a semiconductor wafer is examined by obtaining a first diffraction signal measured using a metrology device. A second diffraction signal is generated using a machine learning system, where the machine learning system receives as an input one or more parameters that characterize a profile of the structure to generate the second diffraction signal. The first and second diffraction signals are compared. When the first and second diffraction signals match within a matching criterion, a feature of the structure is determined based on the one or more parameters or the profile used by the machine learning system to generate the second diffraction signal.
- The present invention can be best understood by reference to the following description taken in conjunction with the accompanying drawing figures, in which like parts may be referred to by like numerals:
- FIG. 1 depicts an exemplary optical metrology system;
- FIGS. 2A-2E depict exemplary profiles;
- FIG. 3 depicts an exemplary neural network;
- FIG. 4 depicts an exemplary process of training a machine learning system;
- FIG. 5 depicts an exemplary process of testing a machine learning system;
- FIG. 6 depicts an exemplary process of determining a feature of a structure using a machine learning system;
- FIG. 7 depicts an exemplary process of determining a feature of a structure using a machine learning system in a library-based process;
- FIG. 8 depicts an exemplary system to determine a feature of a structure using a machine learning system in a library-based system;
- FIG. 9 depicts an exemplary process of determining a feature of a structure using a machine learning system in a regression-based process; and
- FIG. 10 depicts an exemplary system to determine a feature of a structure using a machine learning system in a regression-based system.
- The following description sets forth numerous specific configurations, parameters, and the like. It should be recognized, however, that such description is not intended as a limitation on the scope of the present invention, but is instead provided as a description of exemplary embodiments.
- 1. Metrology
- With reference to FIG. 1, a
metrology system 100 can be used to examine and analyze a structure. For example,metrology system 100 can be used to determine a feature of aperiodic grating 102 formed onwafer 104. As described earlier,periodic grating 102 can be formed in test areas onwafer 104, such as adjacent to a device formed onwafer 104. Alternatively,periodic grating 102 can be formed in an area of the device that does not interfere with the operation of the device or along scribe lines onwafer 104. - As depicted in FIG. 1,
metrology system 100 can include a metrology device with asource 106 and adetector 112.Periodic grating 102 is illuminated by anincident beam 108 fromsource 106. In the present exemplary embodiment,incident beam 108 is directed ontoperiodic grating 102 at an angle of incidence θi with respect to normal n ofperiodic grating 102 and an azimuth angle Φ (i.e., the angle between the plane ofincidence beam 108 and the direction of the periodicity of periodic grating 102).Diffracted beam 110 leaves at an angle of θd with respect to normal {right arrow over (n)} and is received bydetector 112.Detector 112 converts thediffracted beam 110 into a measured diffraction signal, which can include reflectance, tan (Ψ), cos (Δ), Fourier coefficients, and the like. -
Metrology system 100 also includes aprocessing module 114 configured to receive the measured diffraction signal and analyze the measured diffraction signal. As described below, a feature ofperiodic grating 102 can then be determined using a library-based process or a regression-based process. Additionally, other linear or non-linear profile extraction techniques are contemplated. - 2. Library-based Process
- In a library-based process, the measured diffraction signal is compared to a library of diffraction signals. More specifically, each diffraction signal in the library is associated with a profile of the structure. When a match is made between the measured diffraction signal and one of the diffraction signals in the library or when the difference of the measured diffraction signal and one of the diffraction signals in the library is within a preset or matching criterion, the profile associated with the matching diffraction signal in the library is presumed to represent the actual profile of the structure. A feature of the structure can then be determined based on the profile associated with the matching diffraction signal.
- Thus, with reference again to FIG. 1, in one exemplary embodiment, after obtaining a measured diffraction signal,
processing module 114 compares the measured diffraction signal to diffraction signals stored in alibrary 116. Each diffraction signal inlibrary 116 is associated with a profile. When a match is made between the measured diffraction signal and one of the diffraction signals inlibrary 116, the profile associated with the matching diffraction signal inlibrary 116 can be presumed to represent the actual profile ofperiodic grating 102. - The set of profiles stored in
library 116 can be generated by characterizing a profile using a set of parameters, then varying the set of parameters to generate profiles of varying shapes and dimensions. The process of characterizing a profile using a set of parameters can be referred to as parameterizing. - For example, as depicted in FIG. 2A, assume that
profile 200 can be characterized by parameters h1 and w1 that define its height and width, respectively. As depicted in FIGS. 2B to 2E, additional shapes and features ofprofile 200 can be characterized by increasing the number of parameters. For example, as depicted in FIG. 2B,profile 200 can be characterized by parameters h1, w1, and w2 that define its height, bottom width, and top width, respectively. Note that the width ofprofile 200 can be referred to as the critical dimension (CD). For example, in FIG. 2B, parameter w1 and w2 can be described as defining the bottom CD and top CD, respectively, ofprofile 200. It should be recognized that various types of parameters can be used to characterizeprofile 200, including angle of incident (AOI), pitch, n & k, hardware parameters (e.g., polarizer angle), and the like. - As described above, the set of profiles stored in library116 (FIG. 1) can be generated by varying the parameters that characterize the profile. For example, with reference to FIG. 2B, by varying parameters h1, w1, and w2, profiles of varying shapes and dimensions can be generated. Note that one, two, or all three parameters can be varied relative to one another.
- Thus, the parameters of the profile associated with a matching diffraction signal can be used to determine a feature of the structure being examined. For example, a parameter of the profile corresponding to a bottom CD can be used to determine the bottom CD of the structure being examined.
- With reference again to FIG. 1, the number of profiles and corresponding diffraction signals in the set of profiles and diffraction signals stored in library116 (i.e., the resolution and/or range of library 116) depends, in part, on the range over which the set of parameters and the increment at which the set of parameters are varied. In one exemplary embodiment, the profiles and the diffraction signals stored in
library 116 are generated prior to obtaining a measured diffraction signal from an actual structure. Thus, the range and increment (i.e., the range and resolution) used in generatinglibrary 116 can be selected based on familiarity with the fabrication process for a structure and what the range of variance is likely to be. The range and/or resolution oflibrary 116 can also be selected based on empirical measures, such as measurements using atomic force microscopy (AFM), scanning electron microscopy (SEM), and the like. - For a more detailed description of a library-based process, see U.S. patent application Ser. No. 09/907,488, titled GENERATION OF A LIBRARY OF PERIODIC GRATING DIFFR5TION SIGNALS, filed on Jul. 16, 2001, which is incorporated herein by reference in its entirety.
- 3. Regression-based Process
- In a regression-based process, the measured diffraction signal is compared to a diffraction signal generated prior to the comparison (i.e., a trial diffraction signal) using a set of parameters (i.e., trial parameters) for a profile. If the measured diffraction signal and the trial diffraction signal do not match or when the difference of the measured diffraction signal and the trial diffraction signal is not within a preset or matching criterion, another trial diffraction signal is generated using another set of parameters for another profile, then the measured diffraction signal and the newly generated trial diffraction signal are compared. When the measured diffraction signal and the trial diffraction signal match or when the difference of the measured diffraction signal and the trial diffraction signals is within a preset or matching criterion, the profile associated with the matching trial diffraction signal is presumed to represent the actual profile of the structure. The profile associated with the matching trail diffraction signal can then be used to determine a feature of the structure being examined.
- Thus, with reference again to FIG. 1, in one exemplary embodiment,
processing module 114 can generate a trial diffraction signal for a profile, and then compare the measured diffraction signal to the trial diffraction signal. As described above, if the measured diffraction signal and the trial diffraction signal do not match or when the difference of the measured diffraction signal the trial diffraction signals is not within a preset or matching criterion, then processingmodule 114 can iteratively generate another trial diffraction signal for another profile. In one exemplary embodiment, the subsequently generated trial diffraction signal can be generated using an optimization algorithm, such as global optimization techniques, which includes simulated annealing, and local optimization techniques, which includes steepest descent algorithm. - In one exemplary embodiment, the trial diffraction signals and profiles can be stored in a library116 (i.e., a dynamic library). The trial diffraction signals and profiles stored in
library 116 can then be subsequently used in matching the measured diffraction signal. Alternatively,library 116 can be omitted frommetrology system 100. - For a more detailed description of a regression-based process, see U.S. patent application Ser. No. 09/923,578, titled METHOD AND SYSTEM OF DYNAMIC LEARNING THROUGH A REGRESSION-BASED LIBRARY GENERATION PROCESS, filed on Aug. 6, 2001, which is incorporated herein by reference in its entirety.
- 4. Machine Learning Systems
- With reference to FIG. 1, in one exemplary embodiment, diffraction signals used in a library-based process and/or a regression-based process are generated using a
machine learning system 118 employing a machine learning algorithm, such as back-propagation, radial basis function, support vector, kernel regression, and the like. For a more detailed description of machine learning systems and algorithms, see “Neural Networks” by Simon Haykin, Prentice Hall, 1999, which is incorporated herein by reference in its entirety. - In the present exemplary embodiment,
machine learning system 118 receives a profile as an input and generates a diffraction signal as an output. Although in FIG. 1machine learning system 118 is depicted as a component ofprocessing module 114, it should be recognized thatmachine learning system 118 can be a separate module. Moreover, whenmachine learning system 118 is used as part of a library-based process, the diffraction signals inlibrary 116 can be generated in advance bymachine learning system 118. As such,machine learning system 118 can be a separate module that is not connected toprocessing module 114. In contrast, whenmachine learning system 118 is used as part of a regression-based process,machine learning system 118 is connected toprocessing module 114 even whenmachine learning system 118 is a separate module rather than a component ofprocessing module 114. - With reference to FIG. 3, in one exemplary implementation, the machine learning system is a
neural network 300 using a back-propagation algorithm.Neural network 300 includes aninput layer 302, anoutput layer 304, and ahidden layer 306 betweeninput layer 302 andoutput layer 304.Input layer 302 and hiddenlayer 306 are connected usinglinks 308.Hidden layer 306 andoutput layer 304 are connected usinglinks 310. It should be recognized, however, thatneural network 300 can include any number of layers connected in various configurations. - As depicted in FIG. 3,
input layer 302 includes one ormore input nodes 312. In the present exemplary implementation, aninput node 312 ininput layer 302 corresponds to a parameter of the profile that is inputted intoneural network 300. Thus, the number ofinput nodes 312 corresponds to the number of parameters used to characterize the profile. For example, if a profile is characterized using 2 parameters (e.g., top and bottom widths),input layer 302 includes 2input nodes 312, where afirst input node 312 corresponds to a first parameter (e.g., a top width) and asecond input node 312 corresponds to a second parameter (e.g., a bottom width). - In
neural network 300,output layer 304 includes one ormore output nodes 314. In the present exemplary implementation, eachoutput node 314 is a linear function. It should be recognized, however, that eachoutput node 314 can be various types of functions. Additionally, in the present exemplary implementation, anoutput node 314 inoutput layer 304 corresponds to a dimension of the diffraction signal that is outputted fromneural network 300. Thus, the number ofoutput nodes 314 corresponds to the number of dimensions used to characterize the diffraction signal. For example, if a diffraction signal is characterized using 5 dimensions corresponding to, for example, 5 different wavelengths,output layer 304 includes 5output nodes 314, wherein afirst output node 314 corresponds to a first dimension (e.g., a first wavelength), asecond output node 314 corresponds to a second dimension (e.g., a second wavelength), etc. - In
neural network 300, hiddenlayer 306 includes one or morehidden nodes 316. In the present exemplary implementation, eachhidden node 316 is a sigmoidal transfer function or a radial basis function. It should be recognized, however, that eachhidden node 316 can be various types of functions. Additionally, in the present exemplary implementation, the number of hiddennodes 316 is determined based on the number ofoutput nodes 314. More particularly, the number of hidden nodes 316 (m) is related to the number of output nodes 314 (n) by a predetermined ratio (r=m/n). For example, when r=10, there are 10 hiddennodes 316 for eachoutput node 314. It should be recognized, however, that the predetermined ratio can be a ratio of the number ofoutput nodes 314 to the number of hidden nodes 316 (i.e., r=n/m). Additionally, it should be recognized that the number of hiddennodes 316 inneural network 300 can be adjusted after the initial number of hiddennodes 316 is determined based on the predetermined ratio. Furthermore, the number of hiddennodes 316 inneural network 300 can be determined based on experience and/or experimentation rather than based on the predetermined ratio. - Prior to using a machine learning system to generate a diffraction signal, the machine learning system is trained. With reference to FIG. 4, an
exemplary process 400 is depicted for training a machine learning system. Inexemplary process 400, the machine learning system is trained using a set of training input data and a set of training output data, where an input data in the set of training input data has a corresponding output data in the set of training output data to form an input and an output data pair. - In402, the set of training input data is obtained. In the present exemplary embodiment, the training input data includes a set of profiles. As described above, a profile is characterized using a set of parameters. A range of profiles can be generated by varying one or more parameters that characterize a profile, either alone or in combination. An overall range of profiles to be generated is determined based on the expected range of variability in the actual profile of the structure to be examined, which is determined either empirically or through experience. For example, if the actual profile of the structure to be examined is expected to have a bottom width that can vary between x1 and x2, then the overall range of profiles can be generated by varying the parameter corresponding to the bottom width between x1 and x2.
- In one exemplary implementation, the set of profiles used to train the machine learning system is selected from the overall range of profiles to be generated. More particularly, the training data set is selected using a random sampling of the overall range of profiles. It should be recognized that various sampling techniques can be used to select the training data set, such as systematic sampling, a combination of random and systematic sampling, and the like.
- In the present exemplary implementation, the overall range of profiles to be generated is divided into two or more partitions. A machine learning system is configured and trained for each of the partitions. For example, assume the overall range is divided into a first partition and a second partition. Thus, in this example, a first machine learning system is configured and trained for the first partition, and a second machine learning system is configured and trained for the second partition. One advantage of partitioning the overall range and using multiple machine learning systems is that parallel processing can be used (e.g., the two machine learning systems can be trained and used in parallel). Another advantage is that each of the machine learning systems may be more accurate as to their respective partitions than a single machine learning system for the overall range. More specifically, a single machine learning system trained for the overall range may be susceptible to a local minimum that may reduce the accuracy of the machine learning system.
- When the overall range is partitioned, the partitions may be of equal sizes or of varying sizes. When the partitions are of varying sizes, the sizes of the partitions can be determined based on the density of the data within the partitions. For example, a less dense partition may be larger than a more dense partition. It should be recognized that the number and size of the partitions can vary depending on the application.
- In404, the set of training output data is obtained. In the present exemplary embodiment, the training output data includes a set of diffraction signals. A diffraction signal in the set of diffraction signals used as the training output data corresponds to a profile in the set of profiles used as the training input data. Each diffraction signal in the set of diffraction signals can be generated based on each profile in the set of profiles using a modeling technique, such as rigorous coupled wave analysis (RCWA), integral method, Fresnel method, finite analysis, modal analysis, and the like. Alternatively, each diffraction signal in the set of diffraction signals can be generated based on each profile in the set of profiles using an empirical technique, such as measuring a diffraction signal using a metrology device, such as an ellipsometer, reflectometer, atomic force microscope (AFM), scanning electron microscope (SEM), and the like. Thus, a profile from the set of profiles and the corresponding diffraction signal from the set of diffraction signals form a profile/diffraction signal pair. Although there is a one-to-one correspondence between a profile and a diffraction signal in the profile/diffraction signal pair, note that there does not need to be a known relation, either analytic or numeric, between the profile and the diffraction signal in the profile/diffraction signal pair.
- In one exemplary implementation, prior to using the set of diffraction signals to train the machine learning system, the set of diffraction signals is transformed using principal component analysis (PCA). More particularly, a diffraction signal can be characterized using a number of dimensions, such as a number of different wavelengths. By using PCA to transform the set of diffraction signals, the diffraction signals are transformed into uncorrelated dimensions, and the space of the uncorrelated dimensions is smaller than the space of the original dimensions. After the machine learning system has been trained, the diffraction signals can be transformed back.
- In the present exemplary implementation, the dimensions of the diffraction signals can be divided into two or more partitions. A machine learning system is configured and trained for each of the partitions. For example, assume the dimensions are divided into a first partition and a second partition. Thus, in this example, a first machine learning system is configured and trained for the first partition, and a second machine learning system is configured and trained for the second partition. Again, one advantage of partitioning the dimensions and using multiple machine learning systems is that parallel processing can be used (e.g., the two machine learning systems can be trained and used in parallel). Another advantage is that each of the machine learning systems may be more accurate as to their respective partitions than a single machine learning system.
- In406, for a profile from the set of profiles used as the training input data, a diffraction signal is generated using the machine learning system. In 408, the generated diffraction signal is compared with the diffraction signal from the set of diffraction signals that corresponds to the profile. When the difference between the diffraction signals are not within a desired or predetermined margin of error, 406 and 408 are repeated with another profile from the set of profiles used as the training input data. In 410, when the difference between the diffraction signals are within a desired or predetermined margin of error, the training process is terminated.
- It should be recognized that
training process 400 can include the use of an optimization technique, such as gradient descent, linear programming, quadratic programming, simulated annealing, Marquardt-Levenberg algorithm, and the like. Additionally,training process 400 can be performed as a batch process. For a more detailed description of a batch process, see “Neural Networks” by Simon Haykin, which has been cited above. - Furthermore,
training process 400 depicted in FIG. 4 illustrates a back-propagation algorithm. However, it should be recognized that various training algorithms can be used, such as radial basis network, support vector, kernel regression, and the like. - With reference to FIG. 5, an
exemplary process 500 is depicted for testing a machine learning system. In one exemplary embodiment, after a machine learning system has been trained, the machine learning system can be tested to confirm that it has been properly trained. It should be recognized, however, that this testing process can be omitted in some applications. - In502, a set of testing input data is obtained. In 504, a set of testing output data is obtained. In the present exemplary embodiment, the testing input data includes a set of profiles, and the testing output data includes a set of diffraction signals. The set of testing input data and set of testing output data can be obtained using the same process and techniques described above during the training process. The set of testing input data and set of testing output data can be the same as or a subset of the training input data and training output data. Alternatively, the set of testing input data and set of testing out data can be different than the training input data and training output data.
- In506, for a profile from the set of profiles used as the testing input data, a diffraction signal is generated using the machine learning system. In 508, the generated diffraction signal is compared with the diffraction signal from the set of diffraction signals in the testing output data that corresponds to the profile. In 510, when the difference between the diffraction signals are not within a desired or predetermined margin of error, the machine learning system is re-trained. When the machine learning system is re-trained, the training process can be adjusted. For example, the selection and number of the training input and output variables can be adjusted. Additionally, the machine learning system can be adjusted. For example, when the machine learning system is a neural network, as described above, the number of hidden nodes can be adjusted. In 512, when the difference between the diffraction signals are within a desired or predetermined margin of error, the testing process is terminated.
- An empirical risk minimization (ERM) technique can be used to quantify how well the trained machine learning system can generalize to new input. For a more detailed description of ERM, see “Statistical Learning Theory” by Vladimir N. Vapnik, Wiley-Interscience, September 1998, which is incorporated herein by reference in its entirety.
- After the machine learning system has been trained and tested, the machine learning system can be used to generate diffraction signals for use in analyzing a structure formed on a semiconductor wafer. Again, it should be noted that the testing process can be omitted in some applications.
- With reference to FIG. 6, an
exemplary process 600 is depicted for using a machine learning system to examine a structure formed on a semiconductor wafer. In 602, a measured diffraction signal of the structure is obtained by using a metrology device. In 604, a generated diffraction signal is obtained using the machine learning system. In 606, the diffraction signals are compared. In 608, a feature of the structure is determined based on the comparison of the measured and generated diffraction signals. - More particularly, as described above, a profile corresponding to the generated diffraction signal is used as an input to the machine learning system to generate the generated diffraction signal. The profile is characterized by one or more parameters. Thus, when the generated diffraction signal matches the measured diffraction signal within a matching criterion, the profile, and thus the one or more parameters that characterize the profile, can be used to determine a feature of the structure.
- With reference to FIG. 7, an
exemplary process 700 is depicted for using a machine learning system in a library-based process. In 702, a library of diffraction signals are generated using the machine learning system. More particularly, the library of diffraction signals is generated by inputting a range of profiles into the machine learning system. In 704, a measured diffraction signal is obtained using a metrology device, such as an ellipsometer, reflectometer, and the like. In 706, the measured diffraction signal is compared to the diffraction signals in the library of diffraction signals generated using the machine learning system. In 708, a feature of the structure is determined using the profile corresponding to the matching diffraction signal from the library of diffraction signals. - With reference to FIG. 8, an
exemplary system 800 is depicted for using a machine learning system in a library-based system. As depicted in FIG. 8,library 116 is generated usingmachine learning system 118.Library 116 is then used by processingmodule 114 to compare the diffraction signals inlibrary 116 to measured diffraction signals obtained from ametrology device 802, such as an ellipsometer, a reflectometer, and the like. It should be noted that althoughmachine learning system 118 is depicted as a separate unit in FIG. 8,machine learning system 118 can be integrated as a component ofprocessing module 114. Additionally,machine learning system 118 can be connected toprocessing module 114 to transmitlibrary 116 toprocessing module 114, such as through a network connection. Alternatively,library 116 can be stored on a portable storage medium and physically transported toprocessing module 114. - Furthermore, as depicted in FIG. 8,
processing module 114 can be coupled to asemiconductor fabrication unit 804 that is configured to perform one or more fabrication steps. It should be recognized, however, that the metrology system can operate as a stand-alone system in addition to being integrated withsemiconductor fabrication unit 804. - With reference to FIG. 9, an
exemplary process 900 is depicted for using a machine learning system in a regression-based process. In 902, a measured diffraction signal is obtained using a metrology device, such as an ellipsometer, reflectometer, atomic force microscope (AFM), scanning electron microscope (SEM),and the like. In 904, a generated diffraction signal is obtained using the machine learning system. In 906, the two diffraction signals are compared. When the two diffraction signals do not match within a predetermined matching criterion, 904 and 906 are repeated with another diffraction signal generated in 904. This process is iterated until a match is found, meaning that the generated and measured diffraction signals match within the predetermined matching criterion. In 908, if the two diffraction signals match within a predetermined matching criterion, the profile corresponding to the matching diffraction signal is assumed to correspond to the actual profile of the structure being examined. Thus, the profile and the parameters that characterize the profile can be used to determine a feature of the structure. - With reference to FIG. 10, an
exemplary system 1000 is depicted for using a machine learning system in a regression-based system. As depicted in FIG. 10, anoptimizer 1002 receives the measured diffraction signal as an input frommetrology device 802.Optimizer 1002 receives the generated diffraction signal as an input frommachine learning system 118.Optimizer 1002 compares the generated and the measured diffraction signals. When the generated and measured diffraction signals do match,optimizer 1002 outputs the profile corresponding to the matching generated diffraction signal. When the generated and measured diffraction signals do not match within a predetermined matching criterion,optimizer 1002 outputs a signal tomachine learning system 118 to generate another diffraction signal. This process is iterated until a match is found, meaning that the generated and measured diffraction signals match within the predetermined matching criterion. - In one exemplary embodiment, an optimization technique is used to reduce the number of iterations needed to arrive at a match. More particularly, the aim of an optimization problem is to find a best solution among several possible solutions, where the best solution can be quantified by associating a cost function. In other words, for a given problem under a given cost metric, the task is to find a solution with the least cost. Thus, in the present exemplary application, the task is to find the profile with a corresponding diffraction signal that produces the least cost (under a given cost metric) with respect to the given measured diffraction signal. It should be recognized that numerous optimization techniques, which are broadly classified into two categories (i.e., global and local), are known and can be used, such as gradient descent, linear programming, quadratic programming, simulated annealing, Marquardt-Levenberg algorithm, and the like. For a more detailed description of global and local optimization techniques, see “Numerical Recipes in C”, by William H. Press, Saul A. Teukolsky, William T. Vetterling and Brian P. Flannery, Second Edition, Cambridge, which is incorporated herein by reference.
- As described above, a library of diffraction signals can be generated as part of a regression-based process. More particularly, when a match has been made, meaning that the generated diffraction signal and the measured diffraction signal match within the matching criterion, a library of diffraction signals can be generated around the matching profile. Generally, the library of diffraction signals generated as part of the regression-based process is smaller than the library that is generated as part of the library-based process described above.
- Additionally, the library of diffraction signals generated as part of a regression-based process and the library generated as part of a library-based process described above can be used in an interpolation process, where a solution is derived between two entries in the library. For a more detailed description of an interpolation process, see U.S. patent application Ser. No. 10/075,904, titled PROFILE REFINEMENT FOR INTEGRATED CIRCUIT METROLOGY, filed on Feb. 12, 2002, which is incorporated herein by reference in its entirety.
- The foregoing descriptions of specific embodiments of the present invention have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the invention to the precise forms disclosed, and it should be understood that many modifications and variations are possible in light of the above teaching.
- For example, with reference to FIG. 1, as described above,
machine learning system 118 can be configured to operate with a non-optical metrology device, such as an atomic force microscope (AFM), scanning electron microscopes (SEM), and the like, or a combination of an optical and a non-optical metrology device. Thus,machine learning system 118 can generate various types of diffraction signals corresponding to the type of metrology device used. For example, when the metrology device is a SEM, the diffraction signal generated bymachine learning system 118 is a SEM signal, such as two-dimensional images or SEM traces. - Additionally, the diffraction signal generated can include characteristic functions of the signal used by the metrology device. For example, during the training process, various order derivatives (e.g., first order, second order . . . nth order derivatives) of the diffraction signal can be used as part of a Marquardt-Levenberg algorithm to optimize the training process.
Claims (29)
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/608,300 US20040267397A1 (en) | 2003-06-27 | 2003-06-27 | Optical metrology of structures formed on semiconductor wafer using machine learning systems |
CNB2004800149754A CN100418083C (en) | 2003-06-27 | 2004-06-25 | Optical metrology of structures formed on semiconductor wafers using machine learning systems |
PCT/US2004/020682 WO2005003911A2 (en) | 2003-06-27 | 2004-06-25 | Optical metrology of structures formed on semiconductor wafers using machine learning systems |
DE112004001001T DE112004001001T5 (en) | 2003-06-27 | 2004-06-25 | Optical measurement of structures formed on semiconductor wafers using machine learning systems |
JP2006517724A JP4589315B2 (en) | 2003-06-27 | 2004-06-25 | Optical measurement of structures formed on semiconductor wafers using machine learning systems |
KR1020057024949A KR101059427B1 (en) | 2003-06-27 | 2004-06-25 | Optical Measurement of Structures Formed on Semiconductor Wafers Using Machine Learning Systems |
US12/399,011 US7831528B2 (en) | 2003-06-27 | 2009-03-05 | Optical metrology of structures formed on semiconductor wafers using machine learning systems |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/608,300 US20040267397A1 (en) | 2003-06-27 | 2003-06-27 | Optical metrology of structures formed on semiconductor wafer using machine learning systems |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/399,011 Continuation US7831528B2 (en) | 2003-06-27 | 2009-03-05 | Optical metrology of structures formed on semiconductor wafers using machine learning systems |
Publications (1)
Publication Number | Publication Date |
---|---|
US20040267397A1 true US20040267397A1 (en) | 2004-12-30 |
Family
ID=33540544
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/608,300 Abandoned US20040267397A1 (en) | 2003-06-27 | 2003-06-27 | Optical metrology of structures formed on semiconductor wafer using machine learning systems |
US12/399,011 Expired - Fee Related US7831528B2 (en) | 2003-06-27 | 2009-03-05 | Optical metrology of structures formed on semiconductor wafers using machine learning systems |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/399,011 Expired - Fee Related US7831528B2 (en) | 2003-06-27 | 2009-03-05 | Optical metrology of structures formed on semiconductor wafers using machine learning systems |
Country Status (6)
Country | Link |
---|---|
US (2) | US20040267397A1 (en) |
JP (1) | JP4589315B2 (en) |
KR (1) | KR101059427B1 (en) |
CN (1) | CN100418083C (en) |
DE (1) | DE112004001001T5 (en) |
WO (1) | WO2005003911A2 (en) |
Cited By (98)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040017574A1 (en) * | 2002-07-25 | 2004-01-29 | Vi Vuong | Model and parameter selection for optical metrology |
US20050057748A1 (en) * | 2003-09-15 | 2005-03-17 | Timbretechnologies, Inc. | Selecting a hypothetical profile to use in optical metrology |
US20050088665A1 (en) * | 2003-10-28 | 2005-04-28 | Timbre Technologies, Inc. | Azimuthal scanning of a structure formed on a semiconductor wafer |
US20050192914A1 (en) * | 2004-03-01 | 2005-09-01 | Timbre Technologies, Inc. | Selecting a profile model for use in optical metrology using a machine learining system |
US20050209816A1 (en) * | 2004-03-22 | 2005-09-22 | Timbre Technologies, Inc. | Optical metrology optimization for repetitive structures |
US20050275850A1 (en) * | 2004-05-28 | 2005-12-15 | Timbre Technologies, Inc. | Shape roughness measurement in optical metrology |
US20060046166A1 (en) * | 2004-09-01 | 2006-03-02 | Timbre Technologies, Inc. | Controlling critical dimensions of structures formed on a wafer in semiconductor processing |
US20060064280A1 (en) * | 2004-09-21 | 2006-03-23 | Timbre Technologies, Inc. | Optical metrology model optimization based on goals |
US20060119863A1 (en) * | 2004-12-03 | 2006-06-08 | Timbre Technologies, Inc. | Examining a structure formed on a semiconductor wafer using machine learning systems |
US20060181713A1 (en) * | 2005-02-17 | 2006-08-17 | Timbre Technologies, Inc. | Optical metrology of a structure formed on a semiconductor wafer using optical pulses |
US20060187466A1 (en) * | 2005-02-18 | 2006-08-24 | Timbre Technologies, Inc. | Selecting unit cell configuration for repeating structures in optical metrology |
US20060224528A1 (en) * | 2005-03-31 | 2006-10-05 | Timbre Technologies, Inc. | Split machine learning systems |
US20060290947A1 (en) * | 2005-06-16 | 2006-12-28 | Timbre Technologies, Inc. | Optical metrology model optimization for repetitive structures |
US20070002337A1 (en) * | 2005-07-01 | 2007-01-04 | Timbre Technologies, Inc. | Modeling and measuring structures with spatially varying properties in optical metrology |
US20070211260A1 (en) * | 2006-03-08 | 2007-09-13 | Timbre Technologies, Inc. | Weighting function to enhance measured diffraction signals in optical metrology |
US20070225851A1 (en) * | 2004-07-08 | 2007-09-27 | Timbre Technologies, Inc. | Optical metrology model optimization for process control |
US20070225940A1 (en) * | 2006-03-27 | 2007-09-27 | Timbre Technologies Inc. | Library accuracy enhancement and evaluation |
US20070232045A1 (en) * | 2006-03-30 | 2007-10-04 | Tokyo Electron, Ltd. | Damage assessment of a wafer using optical metrology |
US20070229807A1 (en) * | 2006-03-30 | 2007-10-04 | Tokyo Electron, Ltd. | Measuring a damaged structure formed on a wafer using optical metrology |
US20070233404A1 (en) * | 2006-03-30 | 2007-10-04 | Tokyo Electron, Ltd. | Creating a library for measuring a damaged structure formed on a wafer using optical metrology |
US20070229806A1 (en) * | 2006-03-30 | 2007-10-04 | Tokyo Electron, Ltd. | Measuring a damaged structure formed on a wafer using optical metrology |
US20070229855A1 (en) * | 2006-03-30 | 2007-10-04 | Timbre Technologies, Inc. | In-die optical metrology |
US20070229854A1 (en) * | 2006-03-30 | 2007-10-04 | Timbre Technologies, Inc. | Optical metrology of multiple patterned layers |
US20070250200A1 (en) * | 2006-04-21 | 2007-10-25 | Timbre Technologies, Inc. | Optimized characterization of wafers structures for optical metrology |
US20070268498A1 (en) * | 2006-05-22 | 2007-11-22 | Tokyo Electron Limited | Matching optical metrology tools using diffraction signals |
US20070268497A1 (en) * | 2006-05-22 | 2007-11-22 | Tokyo Electron Limited | Matching optical metrology tools using hypothetical profiles |
US7300730B1 (en) | 2006-09-26 | 2007-11-27 | Tokyo Electron Limited | Creating an optically tunable anti-reflective coating |
US20080007740A1 (en) * | 2006-07-10 | 2008-01-10 | Tokyo Electron Limited | Optimizing selected variables of an optical metrology model |
US20080007739A1 (en) * | 2006-07-10 | 2008-01-10 | Tokyo Electron Limited | Optimizing selected variables of an optical metrology system |
US20080007738A1 (en) * | 2006-07-10 | 2008-01-10 | Tokyo Electron Limited | Evaluating a profile model to characterize a structure to be examined using optical metrology |
US20080009081A1 (en) * | 2006-07-10 | 2008-01-10 | Tokyo Electron Limited | Managing and using metrology data for process and equipment control |
US20080016487A1 (en) * | 2006-07-11 | 2008-01-17 | Tokyo Electron Limited | Determining position accuracy of double exposure lithography using optical metrology |
US20080015812A1 (en) * | 2006-07-11 | 2008-01-17 | Tokyo Electron Limited | Parallel profile determination for an optical metrology system |
US20080013107A1 (en) * | 2006-07-11 | 2008-01-17 | Tokyo Electron Limited | Generating a profile model to characterize a structure to be examined using optical metrology |
US20080013108A1 (en) * | 2006-07-11 | 2008-01-17 | Tokyo Electron Limited | Parallel profile determination in optical metrology |
US20080027565A1 (en) * | 2006-07-25 | 2008-01-31 | Tokyo Electron Limited | Allocating processing units to generate simulated diffraction signals used in optical metrology |
US7327475B1 (en) | 2006-12-15 | 2008-02-05 | Tokyo Electron Limited | Measuring a process parameter of a semiconductor fabrication process using optical metrology |
US20080077362A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | Methods and apparatus for using an optically tunable soft mask to create a profile library |
US20080076046A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | accuracy of optical metrology measurements |
US20080076045A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | Methods and apparatus for changing the optical properties of resists |
US20080074678A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | Accuracy of optical metrology measurements |
US20080074677A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | accuracy of optical metrology measurements |
US20080089574A1 (en) * | 2006-10-12 | 2008-04-17 | Tokyo Electron Limited | Data flow management in generating different signal formats used in optical metrology |
US20080091724A1 (en) * | 2006-10-12 | 2008-04-17 | Tokyo Electron Limited | Data flow management in generating profile models used in optical metrology |
US20080106728A1 (en) * | 2006-11-07 | 2008-05-08 | Tokyo Electron Limited | Consecutive measurement of structures formed on a semiconductor wafer using a polarized reflectometer |
US20080106729A1 (en) * | 2006-11-07 | 2008-05-08 | Tokyo Electron Limited | Consecutive measurement of structures formed on a semiconductor wafer using an angle-resolved spectroscopic scatterometer |
US7372583B1 (en) | 2007-04-12 | 2008-05-13 | Tokyo Electron Limited | Controlling a fabrication tool using support vector machine |
US20080115140A1 (en) * | 2006-09-22 | 2008-05-15 | Tokyo Electron Limited | Allocating processing units to processing clusters to generate simulated diffraction signals |
US20080117437A1 (en) * | 2006-11-16 | 2008-05-22 | Tokyo Electron Limited | Drift compensation for an optical metrology tool |
US20080144919A1 (en) * | 2006-12-14 | 2008-06-19 | Tokyo Electron Limited | Determining transmittance of a photomask using optical metrology |
US20080170241A1 (en) * | 2007-01-12 | 2008-07-17 | Tokyo Electron Limited | Automated process control using optical metrology and a correlation between profile models and key profile shape variables |
US20080170242A1 (en) * | 2007-01-12 | 2008-07-17 | Tokyo Electron Limited | Determining one or more profile parameters of a structure using optical metrology and a correlation between profile models and key profile shape variables |
US20080231863A1 (en) * | 2007-03-20 | 2008-09-25 | Tokyo Electron Limited | Automated process control using optical metrology with a photonic nanojet |
US20080241975A1 (en) * | 2007-03-28 | 2008-10-02 | Tokyo Electron Limited | Automated process control using optical metrology and photoresist parameters |
US20080243730A1 (en) * | 2007-03-28 | 2008-10-02 | Tokyo Electron Limited | Training a machine learning system to determine photoresist parameters |
US20080255786A1 (en) * | 2007-04-12 | 2008-10-16 | Tokyo Electron Limited | Optical metrology using support vector machine with profile parameter inputs |
US20080255801A1 (en) * | 2007-04-12 | 2008-10-16 | Tokyo Electron Limited | Optical metrology using a support vector machine with simulated diffraction signal inputs |
US20090063077A1 (en) * | 2007-08-30 | 2009-03-05 | Tokyo Electron Limited | Automated process control using parameters determined with approximation and fine diffraction models |
US20090063076A1 (en) * | 2007-08-30 | 2009-03-05 | Tokyo Electron Limited | Determining profile parameters of a structure using approximation and fine diffraction models in optical metrology |
US7505148B2 (en) | 2006-11-16 | 2009-03-17 | Tokyo Electron Limited | Matching optical metrology tools using spectra enhancement |
US20090083013A1 (en) * | 2007-09-20 | 2009-03-26 | Tokyo Electron Limited | Determining profile parameters of a structure formed on a semiconductor wafer using a dispersion function relating process parameter to dispersion |
US20090082993A1 (en) * | 2007-09-21 | 2009-03-26 | Tokyo Electron Limited | Automated process control of a fabrication tool using a dispersion function relating process parameter to dispersion |
US20090116040A1 (en) * | 2007-11-07 | 2009-05-07 | Tokyo Electron Limited | Method of Deriving an Iso-Dense Bias Using a Hybrid Grating Layer |
US20090118857A1 (en) * | 2007-11-07 | 2009-05-07 | Tokyo Electron Limited | Method of Controlling a Fabrication Process Using an Iso-Dense Bias |
US20090116010A1 (en) * | 2007-11-07 | 2009-05-07 | Tokyo Electron Limited | Apparatus for Deriving an Iso-Dense Bias |
US20090248764A1 (en) * | 2008-03-27 | 2009-10-01 | Paul R Day | Implementing Dynamic Processor Allocation Based Upon Data Density |
US20090287639A1 (en) * | 2008-05-15 | 2009-11-19 | Day Paul R | Embedding Densities in a Data Structure |
US20090287637A1 (en) * | 2008-05-15 | 2009-11-19 | Day Paul R | Determining a Density of a Key Value Referenced in a Database Query Over a Range of Rows |
US20090306941A1 (en) * | 2006-05-15 | 2009-12-10 | Michael Kotelyanskii | Structure Model description and use for scatterometry-based semiconductor manufacturing process metrology |
US20100010765A1 (en) * | 2008-07-08 | 2010-01-14 | Tokyo Electron Limited | System and Method for Azimuth Angle Calibration |
US20100007885A1 (en) * | 2008-07-08 | 2010-01-14 | Tokyo Electron Limited | Pre-Aligned Metrology System and Modules |
US20100007875A1 (en) * | 2008-07-08 | 2010-01-14 | Tokyo Electron Limited | Field Replaceable Units (FRUs) Optimized for Integrated Metrology (IM) |
US20100035168A1 (en) * | 2008-08-08 | 2010-02-11 | Fumiharu Nakajima | Pattern predicting method, recording media and method of fabricating semiconductor device |
US20100042388A1 (en) * | 2008-08-18 | 2010-02-18 | Joerg Bischoff | Computation efficiency by diffraction order truncation |
US7728976B2 (en) | 2007-03-28 | 2010-06-01 | Tokyo Electron Limited | Determining photoresist parameters using optical metrology |
US20100145655A1 (en) * | 2008-12-09 | 2010-06-10 | Hanyou Chu | Rational approximation and continued-fraction approximation approaches for computation efficiency of diffraction signals |
US20100202055A1 (en) * | 2009-02-12 | 2010-08-12 | Tokyo Electron Limited | Diffraction order sorting filter for optical metrology |
US20100201981A1 (en) * | 2009-02-12 | 2010-08-12 | Tokyo Electron Limited | Calibration method for optical metrology |
US20100209830A1 (en) * | 2009-02-13 | 2010-08-19 | Tokyo Electron Limited | Multi-Pitch Scatterometry Targets |
US20100214545A1 (en) * | 2009-02-24 | 2010-08-26 | Tokyo Electron Limited | Creating Metal Gate Structures Using Lithography-Etch-Lithography-Etch (LELE) Processing Sequences |
US20110266440A1 (en) * | 2010-04-29 | 2011-11-03 | Fei Company | SEM Imaging Method |
WO2012048156A3 (en) * | 2010-10-08 | 2012-08-02 | Tokyo Electron Limited | Method of determining an asymmetric property of a structure |
US8464194B1 (en) * | 2011-12-16 | 2013-06-11 | International Business Machines Corporation | Machine learning approach to correct lithographic hot-spots |
US20130325395A1 (en) * | 2012-06-01 | 2013-12-05 | Globalfoundries Singapore Pte. Ltd. | Co-optimization of scatterometry mark design and process monitor mark design |
US8745033B2 (en) | 2008-01-11 | 2014-06-03 | International Business Machines Corporation | Database query optimization using index carryover to subset an index |
US8798966B1 (en) * | 2007-01-03 | 2014-08-05 | Kla-Tencor Corporation | Measuring critical dimensions of a semiconductor structure |
EP2791968A4 (en) * | 2011-12-16 | 2015-06-10 | Kla Tencor Corp | Library generation with derivatives in optical metrology |
US20150235108A1 (en) * | 2014-02-20 | 2015-08-20 | Kla-Tencor Corporation | Signal Response Metrology For Image Based Overlay Measurements |
US20150323316A1 (en) * | 2014-05-09 | 2015-11-12 | Kla-Tencor Corporation | Signal Response Metrology For Scatterometry Based Overlay Measurements |
KR20150136524A (en) * | 2013-03-27 | 2015-12-07 | 케이엘에이-텐코 코포레이션 | Statistical model-based metrology |
US20160341670A1 (en) * | 2015-05-22 | 2016-11-24 | Nanometrics Incorporated | Optical metrology using differential fitting |
CN107077644A (en) * | 2014-11-19 | 2017-08-18 | 科磊股份有限公司 | System, method and computer program product for combining the initial data from multiple metering outfits |
US9977340B2 (en) | 2010-06-04 | 2018-05-22 | Asml Netherlands B.V. | Method and apparatus for measuring a structure on a substrate, computer program products for implementing such methods and apparatus |
DE102018209562B3 (en) | 2018-06-14 | 2019-12-12 | Carl Zeiss Smt Gmbh | Apparatus and methods for inspecting and / or processing an element for photolithography |
WO2020142301A1 (en) * | 2019-01-02 | 2020-07-09 | Kla Corporation | Machine learning for metrology measurements |
US11268805B2 (en) | 2019-02-13 | 2022-03-08 | Kioxia Corporation | Measurement method |
CN114503123A (en) * | 2019-10-14 | 2022-05-13 | 科磊股份有限公司 | Signal domain adaptation for metrology |
US11436693B2 (en) | 2016-10-12 | 2022-09-06 | Fanuc Corporation | Machine learning device and machine learning method for learning correlation between shipment inspection information and operation alarm information for object |
Families Citing this family (57)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7634325B2 (en) * | 2007-05-03 | 2009-12-15 | Taiwan Semiconductor Manufacturing Company, Ltd. | Prediction of uniformity of a wafer |
CN101359611B (en) * | 2007-07-30 | 2011-11-09 | 东京毅力科创株式会社 | Selected variable optimization for optical metering system |
CN101359612B (en) * | 2007-07-30 | 2012-07-04 | 东京毅力科创株式会社 | Managing and using metering data for process and apparatus control |
US7948630B2 (en) * | 2008-10-08 | 2011-05-24 | Tokyo Electron Limited | Auto focus of a workpiece using two or more focus parameters |
KR101467987B1 (en) * | 2009-03-02 | 2014-12-02 | 어플라이드 머티리얼즈 이스라엘 리미티드 | Cd metrology system and method of classifying similar structural elements |
US8603839B2 (en) | 2010-07-23 | 2013-12-10 | First Solar, Inc. | In-line metrology system |
EP2645921B1 (en) | 2010-11-30 | 2019-06-19 | Medivators Inc. | Disposable suction valve for an endoscope |
CN102207424B (en) * | 2010-12-29 | 2013-01-23 | 深圳超多维光电子有限公司 | Parameter measuring system and method of stereo display device |
US8173450B1 (en) | 2011-02-14 | 2012-05-08 | Tokyo Electron Limited | Method of designing an etch stage measurement system |
US8173451B1 (en) | 2011-02-16 | 2012-05-08 | Tokyo Electron Limited | Etch stage measurement system |
US8193007B1 (en) | 2011-02-17 | 2012-06-05 | Tokyo Electron Limited | Etch process control using optical metrology and sensor devices |
US8577820B2 (en) * | 2011-03-04 | 2013-11-05 | Tokyo Electron Limited | Accurate and fast neural network training for library-based critical dimension (CD) metrology |
US8468471B2 (en) | 2011-09-23 | 2013-06-18 | Kla-Tencor Corp. | Process aware metrology |
US10088413B2 (en) * | 2011-11-21 | 2018-10-02 | Kla-Tencor Corporation | Spectral matching based calibration |
US8812277B2 (en) | 2011-12-09 | 2014-08-19 | Tokyo Electron Limited | Method of enhancing an optical metrology system using ray tracing and flexible ray libraries |
US8838422B2 (en) | 2011-12-11 | 2014-09-16 | Tokyo Electron Limited | Process control using ray tracing-based libraries and machine learning systems |
US8570531B2 (en) | 2011-12-11 | 2013-10-29 | Tokyo Electron Limited | Method of regenerating diffraction signals for optical metrology systems |
US10255385B2 (en) | 2012-03-28 | 2019-04-09 | Kla-Tencor Corporation | Model optimization approach based on spectral sensitivity |
US9291554B2 (en) * | 2013-02-05 | 2016-03-22 | Kla-Tencor Corporation | Method of electromagnetic modeling of finite structures and finite illumination for metrology and inspection |
US11175589B2 (en) | 2013-06-03 | 2021-11-16 | Kla Corporation | Automatic wavelength or angle pruning for optical metrology |
US10386729B2 (en) | 2013-06-03 | 2019-08-20 | Kla-Tencor Corporation | Dynamic removal of correlation of highly correlated parameters for optical metrology |
US10481088B2 (en) | 2013-06-04 | 2019-11-19 | Kla-Tencor Corporation | Automatic determination of fourier harmonic order for computation of spectral information for diffraction structures |
US10895810B2 (en) | 2013-11-15 | 2021-01-19 | Kla Corporation | Automatic selection of sample values for optical metrology |
CN104021770B (en) * | 2014-06-12 | 2016-05-11 | 重庆卓美华视光电有限公司 | The processing method of bore hole 3D LCDs module parameter |
US10151986B2 (en) * | 2014-07-07 | 2018-12-11 | Kla-Tencor Corporation | Signal response metrology based on measurements of proxy structures |
US9262819B1 (en) | 2014-09-26 | 2016-02-16 | GlobalFoundries, Inc. | System and method for estimating spatial characteristics of integrated circuits |
US10502549B2 (en) * | 2015-03-24 | 2019-12-10 | Kla-Tencor Corporation | Model-based single parameter measurement |
US11580375B2 (en) | 2015-12-31 | 2023-02-14 | Kla-Tencor Corp. | Accelerated training of a machine learning based model for semiconductor applications |
JP6941103B2 (en) * | 2015-12-31 | 2021-09-29 | ケーエルエー コーポレイション | Accelerated training of machine learning-based models for semiconductor applications |
US10360477B2 (en) * | 2016-01-11 | 2019-07-23 | Kla-Tencor Corp. | Accelerating semiconductor-related computations using learning based models |
US10043261B2 (en) * | 2016-01-11 | 2018-08-07 | Kla-Tencor Corp. | Generating simulated output for a specimen |
US10921369B2 (en) | 2017-01-05 | 2021-02-16 | Xcalipr Corporation | High precision optical characterization of carrier transport properties in semiconductors |
US10733744B2 (en) * | 2017-05-11 | 2020-08-04 | Kla-Tencor Corp. | Learning based approach for aligning images acquired with different modalities |
US11248905B2 (en) * | 2017-08-16 | 2022-02-15 | Kla-Tencor Corporation | Machine learning in metrology measurements |
WO2019177905A1 (en) * | 2018-03-13 | 2019-09-19 | Applied Materials, Inc. | Machine learning systems for monitoring of semiconductor processing |
USD947376S1 (en) | 2018-03-21 | 2022-03-29 | Medivators Inc. | Endoscope suction valve |
WO2019200015A1 (en) | 2018-04-10 | 2019-10-17 | Lam Research Corporation | Optical metrology in machine learning to characterize features |
WO2019212069A1 (en) * | 2018-04-30 | 2019-11-07 | 서울대학교 산학협력단 | Method for predicting structure of indoor space using wireless signal propagation channel analysis through deep learning |
USD952142S1 (en) | 2018-05-21 | 2022-05-17 | Medivators Inc. | Cleaning adapter |
KR102349299B1 (en) | 2018-06-14 | 2022-01-11 | 노바 메주어링 인스트루먼츠 엘티디. | Measurement and process control for semiconductor manufacturing |
EP3629088A1 (en) * | 2018-09-28 | 2020-04-01 | ASML Netherlands B.V. | Providing a trained neural network and determining a characteristic of a physical system |
US10705514B2 (en) | 2018-10-09 | 2020-07-07 | Applied Materials, Inc. | Adaptive chamber matching in advanced semiconductor process control |
US10930531B2 (en) | 2018-10-09 | 2021-02-23 | Applied Materials, Inc. | Adaptive control of wafer-to-wafer variability in device performance in advanced semiconductor processes |
US10657214B2 (en) | 2018-10-09 | 2020-05-19 | Applied Materials, Inc. | Predictive spatial digital design of experiment for advanced semiconductor process optimization and control |
KR102224466B1 (en) | 2018-11-07 | 2021-03-05 | 포항공과대학교 산학협력단 | An analyzing method for perovskite structure using machine learning |
DE102019103503A1 (en) * | 2019-02-12 | 2020-08-13 | Carl Zeiss Smt Gmbh | Error reduction in images that were generated with charged particles using machine learning-based methods |
JP7316867B2 (en) | 2019-07-25 | 2023-07-28 | キオクシア株式会社 | Semiconductor image processing device |
KR102230354B1 (en) * | 2019-11-18 | 2021-03-22 | 고려대학교 산학협력단 | Apparatus and method of testing semiconductor device by using machine learning model |
CN111043988B (en) * | 2019-12-10 | 2021-04-23 | 东南大学 | Single stripe projection measurement method based on graphics and deep learning |
US11092901B2 (en) | 2019-12-21 | 2021-08-17 | Qoniac Gmbh | Wafer exposure method using wafer models and wafer fabrication assembly |
JP6832463B1 (en) * | 2020-04-06 | 2021-02-24 | 東京応化工業株式会社 | Information processing system, information processing device, information processing method and program |
CN111595812B (en) * | 2020-05-29 | 2021-06-22 | 复旦大学 | Method and system for measuring key parameters based on momentum space dispersion relation |
US11289387B2 (en) | 2020-07-31 | 2022-03-29 | Applied Materials, Inc. | Methods and apparatus for backside via reveal processing |
KR102468352B1 (en) * | 2021-02-26 | 2022-11-18 | 김이경 | Structure designing method for controlling wave distribution and apparatus therefor |
US20220375051A1 (en) * | 2021-05-05 | 2022-11-24 | Kla Corporation | Deep generative model-based alignment for semiconductor applications |
US20220388112A1 (en) * | 2021-06-03 | 2022-12-08 | Applied Materials, Inc. | Using light coupling properties for machine-learning-based film detection |
US20240062097A1 (en) * | 2022-08-22 | 2024-02-22 | Applied Materials, Inc. | Equipment parameter management at a manufacturing system using machine learning |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5479573A (en) * | 1992-11-24 | 1995-12-26 | Pavilion Technologies, Inc. | Predictive network with learned preprocessing parameters |
US5793480A (en) * | 1995-09-01 | 1998-08-11 | Phase Metrics, Inc. | Combined interferometer/ellipsometer for measuring small spacings |
US6192103B1 (en) * | 1999-06-03 | 2001-02-20 | Bede Scientific, Inc. | Fitting of X-ray scattering data using evolutionary algorithms |
US6650422B2 (en) * | 2001-03-26 | 2003-11-18 | Advanced Micro Devices, Inc. | Scatterometry techniques to ascertain asymmetry profile of features and generate a feedback or feedforward process control data associated therewith |
US6657736B1 (en) * | 1999-07-09 | 2003-12-02 | Nova Measuring Instruments Ltd. | Method and system for measuring patterned structures |
US6665446B1 (en) * | 1998-12-25 | 2003-12-16 | Canon Kabushiki Kaisha | Image processing apparatus and method |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001185595A (en) * | 1999-12-27 | 2001-07-06 | Fujitsu Ltd | Method for controlling characteristic parameters |
US6943900B2 (en) * | 2000-09-15 | 2005-09-13 | Timbre Technologies, Inc. | Generation of a library of periodic grating diffraction signals |
US6558965B1 (en) * | 2001-07-11 | 2003-05-06 | Advanced Micro Devices, Inc. | Measuring BARC thickness using scatterometry |
US6785638B2 (en) * | 2001-08-06 | 2004-08-31 | Timbre Technologies, Inc. | Method and system of dynamic learning through a regression-based library generation process |
US7031894B2 (en) * | 2002-01-16 | 2006-04-18 | Timbre Technologies, Inc. | Generating a library of simulated-diffraction signals and hypothetical profiles of periodic gratings |
-
2003
- 2003-06-27 US US10/608,300 patent/US20040267397A1/en not_active Abandoned
-
2004
- 2004-06-25 JP JP2006517724A patent/JP4589315B2/en active Active
- 2004-06-25 DE DE112004001001T patent/DE112004001001T5/en not_active Withdrawn
- 2004-06-25 WO PCT/US2004/020682 patent/WO2005003911A2/en active Application Filing
- 2004-06-25 CN CNB2004800149754A patent/CN100418083C/en not_active Expired - Fee Related
- 2004-06-25 KR KR1020057024949A patent/KR101059427B1/en active IP Right Grant
-
2009
- 2009-03-05 US US12/399,011 patent/US7831528B2/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5479573A (en) * | 1992-11-24 | 1995-12-26 | Pavilion Technologies, Inc. | Predictive network with learned preprocessing parameters |
US5793480A (en) * | 1995-09-01 | 1998-08-11 | Phase Metrics, Inc. | Combined interferometer/ellipsometer for measuring small spacings |
US6665446B1 (en) * | 1998-12-25 | 2003-12-16 | Canon Kabushiki Kaisha | Image processing apparatus and method |
US6192103B1 (en) * | 1999-06-03 | 2001-02-20 | Bede Scientific, Inc. | Fitting of X-ray scattering data using evolutionary algorithms |
US6657736B1 (en) * | 1999-07-09 | 2003-12-02 | Nova Measuring Instruments Ltd. | Method and system for measuring patterned structures |
US6650422B2 (en) * | 2001-03-26 | 2003-11-18 | Advanced Micro Devices, Inc. | Scatterometry techniques to ascertain asymmetry profile of features and generate a feedback or feedforward process control data associated therewith |
Cited By (200)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7330279B2 (en) | 2002-07-25 | 2008-02-12 | Timbre Technologies, Inc. | Model and parameter selection for optical metrology |
US7505153B2 (en) | 2002-07-25 | 2009-03-17 | Timbre Technologies, Inc. | Model and parameter selection for optical metrology |
US20080151269A1 (en) * | 2002-07-25 | 2008-06-26 | Timbre Technologies, Inc. | Model and parameter selection for optical metrology |
US20040017574A1 (en) * | 2002-07-25 | 2004-01-29 | Vi Vuong | Model and parameter selection for optical metrology |
US7394554B2 (en) | 2003-09-15 | 2008-07-01 | Timbre Technologies, Inc. | Selecting a hypothetical profile to use in optical metrology |
US20050057748A1 (en) * | 2003-09-15 | 2005-03-17 | Timbretechnologies, Inc. | Selecting a hypothetical profile to use in optical metrology |
US7414733B2 (en) | 2003-10-28 | 2008-08-19 | Timbre Technologies, Inc. | Azimuthal scanning of a structure formed on a semiconductor wafer |
US20050088665A1 (en) * | 2003-10-28 | 2005-04-28 | Timbre Technologies, Inc. | Azimuthal scanning of a structure formed on a semiconductor wafer |
US7224471B2 (en) | 2003-10-28 | 2007-05-29 | Timbre Technologies, Inc. | Azimuthal scanning of a structure formed on a semiconductor wafer |
US20070236705A1 (en) * | 2003-10-28 | 2007-10-11 | Timbre Technologies Inc. | Azimuthal scanning of a structure formed on a semiconductor wafer |
US20050192914A1 (en) * | 2004-03-01 | 2005-09-01 | Timbre Technologies, Inc. | Selecting a profile model for use in optical metrology using a machine learining system |
US7523076B2 (en) * | 2004-03-01 | 2009-04-21 | Tokyo Electron Limited | Selecting a profile model for use in optical metrology using a machine learning system |
US20050209816A1 (en) * | 2004-03-22 | 2005-09-22 | Timbre Technologies, Inc. | Optical metrology optimization for repetitive structures |
US7388677B2 (en) | 2004-03-22 | 2008-06-17 | Timbre Technologies, Inc. | Optical metrology optimization for repetitive structures |
US20050275850A1 (en) * | 2004-05-28 | 2005-12-15 | Timbre Technologies, Inc. | Shape roughness measurement in optical metrology |
US20070225851A1 (en) * | 2004-07-08 | 2007-09-27 | Timbre Technologies, Inc. | Optical metrology model optimization for process control |
US7395132B2 (en) * | 2004-07-08 | 2008-07-01 | Timbre Technologies, Inc. | Optical metrology model optimization for process control |
US7566181B2 (en) | 2004-09-01 | 2009-07-28 | Tokyo Electron Limited | Controlling critical dimensions of structures formed on a wafer in semiconductor processing |
US20060046166A1 (en) * | 2004-09-01 | 2006-03-02 | Timbre Technologies, Inc. | Controlling critical dimensions of structures formed on a wafer in semiconductor processing |
US7171284B2 (en) | 2004-09-21 | 2007-01-30 | Timbre Technologies, Inc. | Optical metrology model optimization based on goals |
US7588949B2 (en) | 2004-09-21 | 2009-09-15 | Tokyo Electron Limited | Optical metrology model optimization based on goals |
US20060064280A1 (en) * | 2004-09-21 | 2006-03-23 | Timbre Technologies, Inc. | Optical metrology model optimization based on goals |
US7453584B2 (en) | 2004-12-03 | 2008-11-18 | Timbre Technologies, Inc. | Examining a structure formed on a semiconductor wafer using machine learning systems |
US20080033683A1 (en) * | 2004-12-03 | 2008-02-07 | Timbre Technologies, Inc. | Examining a structure formed on a semiconductor wafer using machine learning systems |
US7280229B2 (en) | 2004-12-03 | 2007-10-09 | Timbre Technologies, Inc. | Examining a structure formed on a semiconductor wafer using machine learning systems |
US20060119863A1 (en) * | 2004-12-03 | 2006-06-08 | Timbre Technologies, Inc. | Examining a structure formed on a semiconductor wafer using machine learning systems |
US7274465B2 (en) * | 2005-02-17 | 2007-09-25 | Timbre Technologies, Inc. | Optical metrology of a structure formed on a semiconductor wafer using optical pulses |
US20060181713A1 (en) * | 2005-02-17 | 2006-08-17 | Timbre Technologies, Inc. | Optical metrology of a structure formed on a semiconductor wafer using optical pulses |
US20080285054A1 (en) * | 2005-02-18 | 2008-11-20 | Timbre Technologies, Inc. | Optical metrology optimization for repetitive structures |
US7616325B2 (en) | 2005-02-18 | 2009-11-10 | Tokyo Electron Limited | Optical metrology optimization for repetitive structures |
US20060187466A1 (en) * | 2005-02-18 | 2006-08-24 | Timbre Technologies, Inc. | Selecting unit cell configuration for repeating structures in optical metrology |
US20060224528A1 (en) * | 2005-03-31 | 2006-10-05 | Timbre Technologies, Inc. | Split machine learning systems |
US7421414B2 (en) * | 2005-03-31 | 2008-09-02 | Timbre Technologies, Inc. | Split machine learning systems |
US20080195342A1 (en) * | 2005-06-16 | 2008-08-14 | Timbre Technologies, Inc. | Optical metrology model optimization for repetitive structures |
US7355728B2 (en) | 2005-06-16 | 2008-04-08 | Timbre Technologies, Inc. | Optical metrology model optimization for repetitive structures |
US20060290947A1 (en) * | 2005-06-16 | 2006-12-28 | Timbre Technologies, Inc. | Optical metrology model optimization for repetitive structures |
US7515282B2 (en) | 2005-07-01 | 2009-04-07 | Timbre Technologies, Inc. | Modeling and measuring structures with spatially varying properties in optical metrology |
US20070002337A1 (en) * | 2005-07-01 | 2007-01-04 | Timbre Technologies, Inc. | Modeling and measuring structures with spatially varying properties in optical metrology |
US7523021B2 (en) | 2006-03-08 | 2009-04-21 | Tokyo Electron Limited | Weighting function to enhance measured diffraction signals in optical metrology |
US20070211260A1 (en) * | 2006-03-08 | 2007-09-13 | Timbre Technologies, Inc. | Weighting function to enhance measured diffraction signals in optical metrology |
US7302367B2 (en) | 2006-03-27 | 2007-11-27 | Timbre Technologies, Inc. | Library accuracy enhancement and evaluation |
US20070225940A1 (en) * | 2006-03-27 | 2007-09-27 | Timbre Technologies Inc. | Library accuracy enhancement and evaluation |
US7617075B2 (en) | 2006-03-27 | 2009-11-10 | Tokyo Electron Limited | Library accuracy enhancment and evaluation |
US20080071504A1 (en) * | 2006-03-27 | 2008-03-20 | Timbre Technologies Inc. | Library accuracy enhancment and evaluation |
US20070229807A1 (en) * | 2006-03-30 | 2007-10-04 | Tokyo Electron, Ltd. | Measuring a damaged structure formed on a wafer using optical metrology |
US20070229854A1 (en) * | 2006-03-30 | 2007-10-04 | Timbre Technologies, Inc. | Optical metrology of multiple patterned layers |
US7522293B2 (en) | 2006-03-30 | 2009-04-21 | Tokyo Electron Limited | Optical metrology of multiple patterned layers |
US7324193B2 (en) * | 2006-03-30 | 2008-01-29 | Tokyo Electron Limited | Measuring a damaged structure formed on a wafer using optical metrology |
US20080137078A1 (en) * | 2006-03-30 | 2008-06-12 | Tokyo Electron Limited | Measuring a damaged structure formed on a wafer using optical metrology |
US7623978B2 (en) | 2006-03-30 | 2009-11-24 | Tokyo Electron Limited | Damage assessment of a wafer using optical metrology |
US20070229855A1 (en) * | 2006-03-30 | 2007-10-04 | Timbre Technologies, Inc. | In-die optical metrology |
US7619731B2 (en) | 2006-03-30 | 2009-11-17 | Tokyo Electron Limited | Measuring a damaged structure formed on a wafer using optical metrology |
US20070229806A1 (en) * | 2006-03-30 | 2007-10-04 | Tokyo Electron, Ltd. | Measuring a damaged structure formed on a wafer using optical metrology |
US20070233404A1 (en) * | 2006-03-30 | 2007-10-04 | Tokyo Electron, Ltd. | Creating a library for measuring a damaged structure formed on a wafer using optical metrology |
US20070232045A1 (en) * | 2006-03-30 | 2007-10-04 | Tokyo Electron, Ltd. | Damage assessment of a wafer using optical metrology |
US7474420B2 (en) | 2006-03-30 | 2009-01-06 | Timbre Technologies, Inc. | In-die optical metrology |
US7576851B2 (en) | 2006-03-30 | 2009-08-18 | Tokyo Electron Limited | Creating a library for measuring a damaged structure formed on a wafer using optical metrology |
US7444196B2 (en) * | 2006-04-21 | 2008-10-28 | Timbre Technologies, Inc. | Optimized characterization of wafers structures for optical metrology |
US20070250200A1 (en) * | 2006-04-21 | 2007-10-25 | Timbre Technologies, Inc. | Optimized characterization of wafers structures for optical metrology |
WO2007124155A3 (en) * | 2006-04-21 | 2008-11-13 | Tokyo Electron Ltd | Optimized characterization of wafer structures for optical metrology |
WO2007124155A2 (en) * | 2006-04-21 | 2007-11-01 | Tokyo Electron Limited | Optimized characterization of wafer structures for optical metrology |
US20090306941A1 (en) * | 2006-05-15 | 2009-12-10 | Michael Kotelyanskii | Structure Model description and use for scatterometry-based semiconductor manufacturing process metrology |
US7446888B2 (en) | 2006-05-22 | 2008-11-04 | Tokyo Electron Limited | Matching optical metrology tools using diffraction signals |
US7446887B2 (en) | 2006-05-22 | 2008-11-04 | Tokyo Electron Limited | Matching optical metrology tools using hypothetical profiles |
US20070268497A1 (en) * | 2006-05-22 | 2007-11-22 | Tokyo Electron Limited | Matching optical metrology tools using hypothetical profiles |
US20070268498A1 (en) * | 2006-05-22 | 2007-11-22 | Tokyo Electron Limited | Matching optical metrology tools using diffraction signals |
US20080009081A1 (en) * | 2006-07-10 | 2008-01-10 | Tokyo Electron Limited | Managing and using metrology data for process and equipment control |
US7526354B2 (en) | 2006-07-10 | 2009-04-28 | Tokyo Electron Limited | Managing and using metrology data for process and equipment control |
US7495781B2 (en) | 2006-07-10 | 2009-02-24 | Tokyo Electron Limited | Optimizing selected variables of an optical metrology model |
US20080007740A1 (en) * | 2006-07-10 | 2008-01-10 | Tokyo Electron Limited | Optimizing selected variables of an optical metrology model |
US20080007739A1 (en) * | 2006-07-10 | 2008-01-10 | Tokyo Electron Limited | Optimizing selected variables of an optical metrology system |
US7525673B2 (en) | 2006-07-10 | 2009-04-28 | Tokyo Electron Limited | Optimizing selected variables of an optical metrology system |
US20080007738A1 (en) * | 2006-07-10 | 2008-01-10 | Tokyo Electron Limited | Evaluating a profile model to characterize a structure to be examined using optical metrology |
US7518740B2 (en) | 2006-07-10 | 2009-04-14 | Tokyo Electron Limited | Evaluating a profile model to characterize a structure to be examined using optical metrology |
US7515283B2 (en) | 2006-07-11 | 2009-04-07 | Tokyo Electron, Ltd. | Parallel profile determination in optical metrology |
US7523439B2 (en) | 2006-07-11 | 2009-04-21 | Tokyo Electron Limited | Determining position accuracy of double exposure lithography using optical metrology |
US7469192B2 (en) | 2006-07-11 | 2008-12-23 | Tokyo Electron Ltd. | Parallel profile determination for an optical metrology system |
US20080016487A1 (en) * | 2006-07-11 | 2008-01-17 | Tokyo Electron Limited | Determining position accuracy of double exposure lithography using optical metrology |
US20080015812A1 (en) * | 2006-07-11 | 2008-01-17 | Tokyo Electron Limited | Parallel profile determination for an optical metrology system |
US20080013107A1 (en) * | 2006-07-11 | 2008-01-17 | Tokyo Electron Limited | Generating a profile model to characterize a structure to be examined using optical metrology |
US20080013108A1 (en) * | 2006-07-11 | 2008-01-17 | Tokyo Electron Limited | Parallel profile determination in optical metrology |
US7742888B2 (en) | 2006-07-25 | 2010-06-22 | Tokyo Electron Limited | Allocating processing units to generate simulated diffraction signals used in optical metrology |
US20080027565A1 (en) * | 2006-07-25 | 2008-01-31 | Tokyo Electron Limited | Allocating processing units to generate simulated diffraction signals used in optical metrology |
US20080115140A1 (en) * | 2006-09-22 | 2008-05-15 | Tokyo Electron Limited | Allocating processing units to processing clusters to generate simulated diffraction signals |
US7765076B2 (en) | 2006-09-22 | 2010-07-27 | Tokyo Electron Limited | Allocating processing units to processing clusters to generate simulated diffraction signals |
US20080076045A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | Methods and apparatus for changing the optical properties of resists |
US20080074678A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | Accuracy of optical metrology measurements |
US20080076046A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | accuracy of optical metrology measurements |
US20080074677A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | accuracy of optical metrology measurements |
US20080077362A1 (en) * | 2006-09-26 | 2008-03-27 | Tokyo Electron Limited | Methods and apparatus for using an optically tunable soft mask to create a profile library |
US7300730B1 (en) | 2006-09-26 | 2007-11-27 | Tokyo Electron Limited | Creating an optically tunable anti-reflective coating |
US7763404B2 (en) | 2006-09-26 | 2010-07-27 | Tokyo Electron Limited | Methods and apparatus for changing the optical properties of resists |
US7555395B2 (en) | 2006-09-26 | 2009-06-30 | Tokyo Electron Limited | Methods and apparatus for using an optically tunable soft mask to create a profile library |
US20080089574A1 (en) * | 2006-10-12 | 2008-04-17 | Tokyo Electron Limited | Data flow management in generating different signal formats used in optical metrology |
US20080091724A1 (en) * | 2006-10-12 | 2008-04-17 | Tokyo Electron Limited | Data flow management in generating profile models used in optical metrology |
US7765234B2 (en) | 2006-10-12 | 2010-07-27 | Tokyo Electron Limited | Data flow management in generating different signal formats used in optical metrology |
US7783669B2 (en) | 2006-10-12 | 2010-08-24 | Tokyo Electron Limited | Data flow management in generating profile models used in optical metrology |
US7417750B2 (en) | 2006-11-07 | 2008-08-26 | Tokyo Electron Limited | Consecutive measurement of structures formed on a semiconductor wafer using an angle-resolved spectroscopic scatterometer |
US7522295B2 (en) | 2006-11-07 | 2009-04-21 | Tokyo Electron Limited | Consecutive measurement of structures formed on a semiconductor wafer using a polarized reflectometer |
US20080106729A1 (en) * | 2006-11-07 | 2008-05-08 | Tokyo Electron Limited | Consecutive measurement of structures formed on a semiconductor wafer using an angle-resolved spectroscopic scatterometer |
US20080106728A1 (en) * | 2006-11-07 | 2008-05-08 | Tokyo Electron Limited | Consecutive measurement of structures formed on a semiconductor wafer using a polarized reflectometer |
US7428044B2 (en) | 2006-11-16 | 2008-09-23 | Tokyo Electron Limited | Drift compensation for an optical metrology tool |
US20080117437A1 (en) * | 2006-11-16 | 2008-05-22 | Tokyo Electron Limited | Drift compensation for an optical metrology tool |
US7505148B2 (en) | 2006-11-16 | 2009-03-17 | Tokyo Electron Limited | Matching optical metrology tools using spectra enhancement |
US20080144919A1 (en) * | 2006-12-14 | 2008-06-19 | Tokyo Electron Limited | Determining transmittance of a photomask using optical metrology |
US7639375B2 (en) | 2006-12-14 | 2009-12-29 | Tokyo Electron Limited | Determining transmittance of a photomask using optical metrology |
US20080212080A1 (en) * | 2006-12-15 | 2008-09-04 | Tokyo Electron Limited | Measuring a process parameter of a semiconductor fabrication process using optical metrology |
US7522294B2 (en) | 2006-12-15 | 2009-04-21 | Tokyo Electron Limited | Measuring a process parameter of a semiconductor fabrication process using optical metrology |
US7327475B1 (en) | 2006-12-15 | 2008-02-05 | Tokyo Electron Limited | Measuring a process parameter of a semiconductor fabrication process using optical metrology |
US8798966B1 (en) * | 2007-01-03 | 2014-08-05 | Kla-Tencor Corporation | Measuring critical dimensions of a semiconductor structure |
US20080170241A1 (en) * | 2007-01-12 | 2008-07-17 | Tokyo Electron Limited | Automated process control using optical metrology and a correlation between profile models and key profile shape variables |
US20080170242A1 (en) * | 2007-01-12 | 2008-07-17 | Tokyo Electron Limited | Determining one or more profile parameters of a structure using optical metrology and a correlation between profile models and key profile shape variables |
US7667858B2 (en) | 2007-01-12 | 2010-02-23 | Tokyo Electron Limited | Automated process control using optical metrology and a correlation between profile models and key profile shape variables |
US7596422B2 (en) | 2007-01-12 | 2009-09-29 | Tokyo Electron Limited | Determining one or more profile parameters of a structure using optical metrology and a correlation between profile models and key profile shape variables |
US20080231863A1 (en) * | 2007-03-20 | 2008-09-25 | Tokyo Electron Limited | Automated process control using optical metrology with a photonic nanojet |
US7639351B2 (en) | 2007-03-20 | 2009-12-29 | Tokyo Electron Limited | Automated process control using optical metrology with a photonic nanojet |
US7567353B2 (en) | 2007-03-28 | 2009-07-28 | Tokyo Electron Limited | Automated process control using optical metrology and photoresist parameters |
US20080241975A1 (en) * | 2007-03-28 | 2008-10-02 | Tokyo Electron Limited | Automated process control using optical metrology and photoresist parameters |
US7949618B2 (en) | 2007-03-28 | 2011-05-24 | Tokyo Electron Limited | Training a machine learning system to determine photoresist parameters |
US20080243730A1 (en) * | 2007-03-28 | 2008-10-02 | Tokyo Electron Limited | Training a machine learning system to determine photoresist parameters |
US7728976B2 (en) | 2007-03-28 | 2010-06-01 | Tokyo Electron Limited | Determining photoresist parameters using optical metrology |
US7372583B1 (en) | 2007-04-12 | 2008-05-13 | Tokyo Electron Limited | Controlling a fabrication tool using support vector machine |
US7483809B2 (en) | 2007-04-12 | 2009-01-27 | Tokyo Electron Limited | Optical metrology using support vector machine with profile parameter inputs |
US7567352B2 (en) | 2007-04-12 | 2009-07-28 | Tokyo Electron Limited | Controlling a fabrication tool using support vector machine |
US20080255801A1 (en) * | 2007-04-12 | 2008-10-16 | Tokyo Electron Limited | Optical metrology using a support vector machine with simulated diffraction signal inputs |
US20080252908A1 (en) * | 2007-04-12 | 2008-10-16 | Tokyo Electron Limited | Controlling a fabrication tool using support vector machine |
US7511835B2 (en) | 2007-04-12 | 2009-03-31 | Tokyo Electron Limited | Optical metrology using a support vector machine with simulated diffraction signal inputs |
US20080255786A1 (en) * | 2007-04-12 | 2008-10-16 | Tokyo Electron Limited | Optical metrology using support vector machine with profile parameter inputs |
US7949490B2 (en) | 2007-08-30 | 2011-05-24 | Tokyo Electron Limited | Determining profile parameters of a structure using approximation and fine diffraction models in optical metrology |
US7627392B2 (en) | 2007-08-30 | 2009-12-01 | Tokyo Electron Limited | Automated process control using parameters determined with approximation and fine diffraction models |
US20090063076A1 (en) * | 2007-08-30 | 2009-03-05 | Tokyo Electron Limited | Determining profile parameters of a structure using approximation and fine diffraction models in optical metrology |
US20090063077A1 (en) * | 2007-08-30 | 2009-03-05 | Tokyo Electron Limited | Automated process control using parameters determined with approximation and fine diffraction models |
US7912679B2 (en) * | 2007-09-20 | 2011-03-22 | Tokyo Electron Limited | Determining profile parameters of a structure formed on a semiconductor wafer using a dispersion function relating process parameter to dispersion |
US20090083013A1 (en) * | 2007-09-20 | 2009-03-26 | Tokyo Electron Limited | Determining profile parameters of a structure formed on a semiconductor wafer using a dispersion function relating process parameter to dispersion |
US20090082993A1 (en) * | 2007-09-21 | 2009-03-26 | Tokyo Electron Limited | Automated process control of a fabrication tool using a dispersion function relating process parameter to dispersion |
US7636649B2 (en) * | 2007-09-21 | 2009-12-22 | Tokyo Electron Limited | Automated process control of a fabrication tool using a dispersion function relating process parameter to dispersion |
US20090116010A1 (en) * | 2007-11-07 | 2009-05-07 | Tokyo Electron Limited | Apparatus for Deriving an Iso-Dense Bias |
US7639370B2 (en) | 2007-11-07 | 2009-12-29 | Tokyo Electron Limited | Apparatus for deriving an iso-dense bias |
US20090118857A1 (en) * | 2007-11-07 | 2009-05-07 | Tokyo Electron Limited | Method of Controlling a Fabrication Process Using an Iso-Dense Bias |
US7598099B2 (en) | 2007-11-07 | 2009-10-06 | Tokyo Electron Limited | Method of controlling a fabrication process using an iso-dense bias |
US20090116040A1 (en) * | 2007-11-07 | 2009-05-07 | Tokyo Electron Limited | Method of Deriving an Iso-Dense Bias Using a Hybrid Grating Layer |
US8745033B2 (en) | 2008-01-11 | 2014-06-03 | International Business Machines Corporation | Database query optimization using index carryover to subset an index |
US8015191B2 (en) * | 2008-03-27 | 2011-09-06 | International Business Machines Corporation | Implementing dynamic processor allocation based upon data density |
US20090248764A1 (en) * | 2008-03-27 | 2009-10-01 | Paul R Day | Implementing Dynamic Processor Allocation Based Upon Data Density |
US20090287639A1 (en) * | 2008-05-15 | 2009-11-19 | Day Paul R | Embedding Densities in a Data Structure |
US10387411B2 (en) | 2008-05-15 | 2019-08-20 | International Business Machines Corporation | Determining a density of a key value referenced in a database query over a range of rows |
US8140520B2 (en) | 2008-05-15 | 2012-03-20 | International Business Machines Corporation | Embedding densities in a data structure |
US8396861B2 (en) | 2008-05-15 | 2013-03-12 | International Business Machines Corporation | Determining a density of a key value referenced in a database query over a range of rows |
US8275761B2 (en) | 2008-05-15 | 2012-09-25 | International Business Machines Corporation | Determining a density of a key value referenced in a database query over a range of rows |
US20090287637A1 (en) * | 2008-05-15 | 2009-11-19 | Day Paul R | Determining a Density of a Key Value Referenced in a Database Query Over a Range of Rows |
US20100007885A1 (en) * | 2008-07-08 | 2010-01-14 | Tokyo Electron Limited | Pre-Aligned Metrology System and Modules |
US7990534B2 (en) | 2008-07-08 | 2011-08-02 | Tokyo Electron Limited | System and method for azimuth angle calibration |
US20100010765A1 (en) * | 2008-07-08 | 2010-01-14 | Tokyo Electron Limited | System and Method for Azimuth Angle Calibration |
US7940391B2 (en) | 2008-07-08 | 2011-05-10 | Tokyo Electron Limited | Pre-aligned metrology system and modules |
US7742163B2 (en) | 2008-07-08 | 2010-06-22 | Tokyo Electron Limited | Field replaceable units (FRUs) optimized for integrated metrology (IM) |
US20100007875A1 (en) * | 2008-07-08 | 2010-01-14 | Tokyo Electron Limited | Field Replaceable Units (FRUs) Optimized for Integrated Metrology (IM) |
US20100035168A1 (en) * | 2008-08-08 | 2010-02-11 | Fumiharu Nakajima | Pattern predicting method, recording media and method of fabricating semiconductor device |
US20100042388A1 (en) * | 2008-08-18 | 2010-02-18 | Joerg Bischoff | Computation efficiency by diffraction order truncation |
US9625937B2 (en) | 2008-08-18 | 2017-04-18 | Kla-Tencor Corporation | Computation efficiency by diffraction order truncation |
US20100145655A1 (en) * | 2008-12-09 | 2010-06-10 | Hanyou Chu | Rational approximation and continued-fraction approximation approaches for computation efficiency of diffraction signals |
US8560270B2 (en) * | 2008-12-09 | 2013-10-15 | Tokyo Electron Limited | Rational approximation and continued-fraction approximation approaches for computation efficiency of diffraction signals |
US20100201981A1 (en) * | 2009-02-12 | 2010-08-12 | Tokyo Electron Limited | Calibration method for optical metrology |
US7924422B2 (en) | 2009-02-12 | 2011-04-12 | Tokyo Electron Limited | Calibration method for optical metrology |
US8107073B2 (en) | 2009-02-12 | 2012-01-31 | Tokyo Electron Limited | Diffraction order sorting filter for optical metrology |
US20100202055A1 (en) * | 2009-02-12 | 2010-08-12 | Tokyo Electron Limited | Diffraction order sorting filter for optical metrology |
US20100209830A1 (en) * | 2009-02-13 | 2010-08-19 | Tokyo Electron Limited | Multi-Pitch Scatterometry Targets |
US8024676B2 (en) | 2009-02-13 | 2011-09-20 | Tokyo Electron Limited | Multi-pitch scatterometry targets |
US8183062B2 (en) | 2009-02-24 | 2012-05-22 | Tokyo Electron Limited | Creating metal gate structures using Lithography-Etch-Lithography-Etch (LELE) processing sequences |
US20100214545A1 (en) * | 2009-02-24 | 2010-08-26 | Tokyo Electron Limited | Creating Metal Gate Structures Using Lithography-Etch-Lithography-Etch (LELE) Processing Sequences |
US8232523B2 (en) * | 2010-04-29 | 2012-07-31 | Fei Company | SEM imaging method |
US20110266440A1 (en) * | 2010-04-29 | 2011-11-03 | Fei Company | SEM Imaging Method |
US9977340B2 (en) | 2010-06-04 | 2018-05-22 | Asml Netherlands B.V. | Method and apparatus for measuring a structure on a substrate, computer program products for implementing such methods and apparatus |
US9239522B2 (en) | 2010-10-08 | 2016-01-19 | Kla-Tencor Corporation | Method of determining an asymmetric property of a structure |
WO2012048156A3 (en) * | 2010-10-08 | 2012-08-02 | Tokyo Electron Limited | Method of determining an asymmetric property of a structure |
US8464194B1 (en) * | 2011-12-16 | 2013-06-11 | International Business Machines Corporation | Machine learning approach to correct lithographic hot-spots |
EP2791968A4 (en) * | 2011-12-16 | 2015-06-10 | Kla Tencor Corp | Library generation with derivatives in optical metrology |
US20130325395A1 (en) * | 2012-06-01 | 2013-12-05 | Globalfoundries Singapore Pte. Ltd. | Co-optimization of scatterometry mark design and process monitor mark design |
KR20150136524A (en) * | 2013-03-27 | 2015-12-07 | 케이엘에이-텐코 코포레이션 | Statistical model-based metrology |
US10101670B2 (en) | 2013-03-27 | 2018-10-16 | Kla-Tencor Corporation | Statistical model-based metrology |
KR102035376B1 (en) | 2013-03-27 | 2019-10-23 | 케이엘에이 코포레이션 | Statistical model-based metrology |
EP2979297A4 (en) * | 2013-03-27 | 2017-02-22 | Kla-Tencor Corporation | Statistical model-based metrology |
KR20160124775A (en) * | 2014-02-20 | 2016-10-28 | 케이엘에이-텐코 코포레이션 | Signal response metrology for image based overlay measurements |
US10152654B2 (en) * | 2014-02-20 | 2018-12-11 | Kla-Tencor Corporation | Signal response metrology for image based overlay measurements |
US20150235108A1 (en) * | 2014-02-20 | 2015-08-20 | Kla-Tencor Corporation | Signal Response Metrology For Image Based Overlay Measurements |
KR102184029B1 (en) | 2014-02-20 | 2020-11-27 | 케이엘에이 코포레이션 | Signal response metrology for image based overlay measurements |
KR102221063B1 (en) | 2014-05-09 | 2021-02-25 | 케이엘에이 코포레이션 | Signal response metrology for scatterometry based overlay measurements |
KR20170005059A (en) * | 2014-05-09 | 2017-01-11 | 케이엘에이-텐코 코포레이션 | Signal response metrology for scatterometry based overlay measurements |
US10352876B2 (en) * | 2014-05-09 | 2019-07-16 | KLA—Tencor Corporation | Signal response metrology for scatterometry based overlay measurements |
US20150323316A1 (en) * | 2014-05-09 | 2015-11-12 | Kla-Tencor Corporation | Signal Response Metrology For Scatterometry Based Overlay Measurements |
CN107077644A (en) * | 2014-11-19 | 2017-08-18 | 科磊股份有限公司 | System, method and computer program product for combining the initial data from multiple metering outfits |
US9995689B2 (en) * | 2015-05-22 | 2018-06-12 | Nanometrics Incorporated | Optical metrology using differential fitting |
US20160341670A1 (en) * | 2015-05-22 | 2016-11-24 | Nanometrics Incorporated | Optical metrology using differential fitting |
US11436693B2 (en) | 2016-10-12 | 2022-09-06 | Fanuc Corporation | Machine learning device and machine learning method for learning correlation between shipment inspection information and operation alarm information for object |
DE102018209562B3 (en) | 2018-06-14 | 2019-12-12 | Carl Zeiss Smt Gmbh | Apparatus and methods for inspecting and / or processing an element for photolithography |
US11410290B2 (en) | 2019-01-02 | 2022-08-09 | Kla Corporation | Machine learning for metrology measurements |
WO2020142301A1 (en) * | 2019-01-02 | 2020-07-09 | Kla Corporation | Machine learning for metrology measurements |
US20220318987A1 (en) * | 2019-01-02 | 2022-10-06 | Kla Corporation | Machine Learning for Metrology Measurements |
US11783466B2 (en) * | 2019-01-02 | 2023-10-10 | Kla Corporation | Machine learning for metrology measurements |
US11268805B2 (en) | 2019-02-13 | 2022-03-08 | Kioxia Corporation | Measurement method |
CN114503123A (en) * | 2019-10-14 | 2022-05-13 | 科磊股份有限公司 | Signal domain adaptation for metrology |
Also Published As
Publication number | Publication date |
---|---|
WO2005003911A3 (en) | 2005-06-30 |
WO2005003911A2 (en) | 2005-01-13 |
CN100418083C (en) | 2008-09-10 |
CN1799045A (en) | 2006-07-05 |
KR101059427B1 (en) | 2011-08-25 |
US7831528B2 (en) | 2010-11-09 |
US20090198635A1 (en) | 2009-08-06 |
JP4589315B2 (en) | 2010-12-01 |
DE112004001001T5 (en) | 2006-09-14 |
JP2007528985A (en) | 2007-10-18 |
KR20060033740A (en) | 2006-04-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7831528B2 (en) | Optical metrology of structures formed on semiconductor wafers using machine learning systems | |
US7523076B2 (en) | Selecting a profile model for use in optical metrology using a machine learning system | |
US7453584B2 (en) | Examining a structure formed on a semiconductor wafer using machine learning systems | |
TWI509431B (en) | Method for automated determination of an optimally parameterized scatterometry model | |
US7372583B1 (en) | Controlling a fabrication tool using support vector machine | |
CN107092958B (en) | Accurate and fast neural network training for library-based critical dimension CD metrology | |
US7523021B2 (en) | Weighting function to enhance measured diffraction signals in optical metrology | |
KR101144402B1 (en) | Method and system of selecting a hypothetical profile to use in optical metrology, and computer readable storage medium therefor | |
EP1541960A2 (en) | Parametric optimization of optical metrology model | |
US20130110477A1 (en) | Process variation-based model optimization for metrology | |
US20130158957A1 (en) | Library generation with derivatives in optical metrology | |
US7483809B2 (en) | Optical metrology using support vector machine with profile parameter inputs | |
CN106030282B (en) | Method for automatic wavelength or angle pruning for optical metrology and optical system | |
US10386729B2 (en) | Dynamic removal of correlation of highly correlated parameters for optical metrology | |
US7522295B2 (en) | Consecutive measurement of structures formed on a semiconductor wafer using a polarized reflectometer | |
US20080106729A1 (en) | Consecutive measurement of structures formed on a semiconductor wafer using an angle-resolved spectroscopic scatterometer | |
US20080255801A1 (en) | Optical metrology using a support vector machine with simulated diffraction signal inputs | |
US7446887B2 (en) | Matching optical metrology tools using hypothetical profiles | |
US7446888B2 (en) | Matching optical metrology tools using diffraction signals | |
KR101179300B1 (en) | Examining a structure formed on a semiconductor wafer using machine learning systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: TIMBRE TECHNOLOGIES, INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:DODDI, SRINIVAS;DREGE, EMMANUEL;JAKATDAR, NICKHIL;AND OTHERS;REEL/FRAME:014257/0857 Effective date: 20030627 |
|
AS | Assignment |
Owner name: TOKYO ELECTRON LIMITED, JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:TIMBRE TECHNOLOGIES, INC.;REEL/FRAME:022388/0109 Effective date: 20090312 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |