Tokyo Electron Limited

Timbre Technologies, Inc.

Kla Tencor Corporation

Vi Vuong

Junwei Bao

Yan Chen

Emmanuel Drege

Srinivas Rao Doddi

Nickhil Jakatdar

Shifang Li

Manuel B Madriaga

Wen Jin

Hong Qiu

Hemalatha Erva

Lawrence Lane

Sebastien Egret

Wei Liu

Gang He

Leonid Poslavsky

Sanjay K Yedur

Xinhui Niu

Hanyou Chu

Xinkang Tian

Joerg Bischoff

Holger Tuitje

Lie-Quan Lee

Jeffrey Alexander Chard

Serguei Komarov

Kelly Barry

Weichert Heiko

Miao Liu

Walter Dean Mieher

Daniel Joseph Prager

Ching-Ling Meng

Mihail Mihaylov

Jason Ferns

Joel Ng

Zheng Yan

Heiko Weichert

Michael Laughery

Alan Nolet

Mike Laughery

Jin Wen

Doris Chin

Shifang Ll

Raghu Balasubramanian

Badru D Hyatt

Described is a method for determining an endpoint of an etch process using optical emission spectroscopy (OES) data as an input. OES data is acquired by a spectrometer in a plasma etch processing chamber. The acquired time-evolving spectral data is first filtered and de-meaned, and thereafter transformed into transformed spectral data, or trends, using multivariate analysis such as principal components analysis, in which previously calculated principal component weights are used to accomplish the transform. Grouping of the principal components weights into two separate groups corresponding to positive and negative natural wavelengths, creates separate signed trends (synthetic wavelengths).

Synthetic wavelengths for endpoint detection in plasma etching

An advanced optical sensor and method for detection of optical events in a plasma processing system. The method includes detecting at least one light emission signal in a plasma processing chamber. The at least one detected light emission signal including light emissions from an optical event. The method further includes processing the at least one light emission signal and detecting a signature of the optical event from the processed light emission signal.

Advanced optical sensor and method for detecting an optical event in a light emission signal in a plasma chamber

Described is a method for determining an endpoint of an etch process using optical emission spectroscopy (OES) data as an input. Optical emission spectroscopy (OES) data are acquired by a spectrometer attached to a plasma etch processing tool. The acquired time-evolving spectral data are first filtered and demeaned, and thereafter transformed into transformed spectral data, or trends, using multivariate analysis such as principal components analysis, in which previously calculated principal component weights are used to accomplish the transform. A functional form incorporating multiple trends may be used to more precisely determine the endpoint of an etch process. A method for calculating principal component weights prior to actual etching, based on OES data collected from previous etch processing, is disclosed, which method facilitates rapid calculation of trends and functional forms involving multiple trends, for efficient and accurate in-line determination of etch process endpoint.

Method of endpoint detection of plasma etching process using multivariate analysis

Embodiments are generally directed to neural network training for library-based critical dimension metrology. An embodiment of a method includes optimizing a threshold for a principal component analysis of a spectrum data set to provide a principal component value, estimating a training target for one or more neural networks, training the one or more neural networks based both on the training target and on the principal component value provided from optimizing the threshold for the principal component analysis, and providing a spectral library based on the one or more trained neural networks.

Accurate and fast neural network training for library-based critical dimension (CD) metrology

Disclosed is a method for determining an endpoint of an etch process using optical emission spectroscopy (OES) data as an input. Optical emission spectroscopy (OES) data are acquired by a spectrometer attached to a plasma etch processing tool. The acquired time-evolving spectral data are first filtered and demeaned, and thereafter transformed into transformed spectral data, or trends, using multivariate analysis such as principal components analysis, in which previously calculated principal component weights are used to accomplish the transform. A functional form incorporating multiple trends may be used to more precisely determine the endpoint of an etch process. A method for calculating principal component weights prior to actual etching, based on OES data collected from previous etch processing, is disclosed, which method facilitates rapid calculation of trends and functional forms involving multiple trends, for efficient and accurate in-line determination of etch process endpoint.

Approaches for accurate neural network training for library-based critical dimension (CD) metrology are described. Approaches for fast neural network training for library-based CD metrology are also described. In an example, a method includes optimizing a threshold for a principal component analysis (PCA) of a spectrum data set to provide a principal component (PC) value, estimating a training target for one or more neural networks, training the one or more neural networks based both on the training target and on the PC value provided from optimizing the threshold for the PCA, and providing a spectral library based on the one or more trained neural networks.

Automated determination of a number of profiles for a training data set to be used in training a machine learning system for generating target function information from modeled profile parameters. In one embodiment, a first principal component analysis (PCA) is performed on a training data set, and a second PCA is performed on a combined data set which includes the training data set and a test data set. A test data set estimate is generated based on the first PCA transform and the second PCA matrix. The size of error between the test data set and the test data set estimate is used to determine whether a number of profiles associated with the training data set is sufficiently large for training a machine learning system to generate a library of spectral information.

Determination of training set size for a machine learning system

Metrology data from a semiconductor treatment system is transformed using multivariate analysis. In particular, a set of metrology data measured or simulated for one or more substrates treated using the treatment system is obtained. One or more essential variables for the obtained set of metrology data is determined using multivariate analysis. A first metrology data measured or simulated for one or more substrates treated using the treatment system is obtained. The first obtained metrology data is not one of the metrology data in the set of metrology data earlier obtained. The first metrology data is transformed into a second metrology data using the one or more of the determined essential variables.

Transforming metrology data from a semiconductor treatment system using multivariate analysis

To manage data flow in generating profile models for use in optical metrology, a project data object is created. A first profile model data object is created. The first profile model data object corresponds to a first profile model defined using profile parameters. A version number is associated with the first profile model data object. The first profile model data object is linked with the project data object. At least a second profile model data object is created. The second profile model data object corresponds to a second profile model defined using profile parameters. The first and second profile models are different. Another version number is associated with the second profile model data object. The second profile model data object is linked with the project data object. The project data object, the first profile model data object, and the second profile model data object are stored. The version numbers associated with the first profile model data object and the second profile model data object are stored. The link between the first profile model data object and the project data object is stored. The link between the second profile model data object and the project data object is stored.

Data flow management in generating profile models used in optical metrology

In allocating processing units, first and second requests for jobs are obtained. First and second numbers of processing units requested are determined. First and second numbers of available processing units are determined. When the first number of available processing units is non-zero, the first number of available number of processing units or the first number of processing units requested is assigned to a first processing cluster. A first processing unit in the first processing cluster is designated as a master node. When the second number of available processing units is non-zero, the second number of available number of processing units or the second number of processing units requested is assigned to a second processing cluster. The first processing unit in the second processing cluster is designated as a slave node. The first and second jobs are assigned to the first and second processing clusters, respectively.

Allocating processing units to processing clusters to generate simulated diffraction signals

To manage data flow in generating different signal formats for use in optical metrology, a project data object is created. A first option data object is created. The first option data object has a set of signal parameters. Different settings of the set of signal parameters correspond to different signal formats for diffraction signals. A version number is associated with the first option data object. The first option data object is linked with the project data object. At least a second option data object is created. The second option data object has a set of signal parameters. Different settings of the set of signal parameters correspond to different signal formats for diffraction signals. The set of signal parameters of the first option data object and the set of signal parameters of the second option data object are set differently. Another version number is associated with the second option data object. The second option data object is linked with the project data object. The project data object, the first option data object, and the second option data object are stored. The version numbers associated with the first option data object and the second option data object are stored. The link between the first option data object and the project data object is stored. The link between the second option data object and the project data object is stored.

Data flow management in generating different signal formats used in optical metrology

In allocating processing units of a computer system to generate simulated diffraction signals used in optical metrology, a request for a job to generate simulated diffraction signals using multiple processing units is obtained. A number of processing units requested for the job to generate simulated diffraction signals is then determined. A number of available processing units is determined. When the number of processing units requested is greater than the number of available processing units, a number of processing units is assigned to generate the simulated diffraction signals that is less than the number of processing units requested.

Allocating processing units to generate simulated diffraction signals used in optical metrology

An optical metrology model for a structure to be formed on a wafer is developed by characterizing a top-view profile and a cross-sectional view profile of the structure using profile parameters. The profile parameters of the top-view profile and the cross-sectional view profile are integrated together into the optical metrology model. The profile parameters of the optical metrology model are saved.

Optical metrology optimization for repetitive structures

The optimization of an optical metrology model for use in measuring a wafer structure is evaluated. An optical metrology model having metrology model variables, which includes profile model parameters of a profile model, is developed. One or more goals for metrology model optimization are selected. One or more profile model parameters to be used in evaluating the one or more selected goals are selected. One or more metrology model variables to be set to fixed values are selected. One or more selected metrology model variables are set to fixed values. One or more termination criteria for the one or more selected goals are set. The optical metrology model is optimized using the fixed values for the one or more selected metrology model variables. Measurements for the one or more selected profile model parameters are obtained using the optimized optical metrology model. A determination is then made as to whether the one or more termination criteria are met by the obtained measurements.

Optical metrology model optimization based on goals

Growing community of inventors

Fremont, CA, United States of America

Vi Vuong