公开(公告)号：WO2020074162A1

公开(公告)日：2020-04-16

申请号：PCT/EP2019/072355

申请日：2019-08-21

Applicant: ASML NETHERLANDS B.V.

Inventor： MOSSAVAT, Seyed Iman ,  FAGGINGER AUER, Bastiaan, Onne ,  DIRKS, Remco ,  ONOSE, Alexandru ,  CRAMER, Hugo, Augustinus, Joseph

IPC: G03F7/20

Abstract: Methods for calibrating metrology apparatuses and determining a parameter of interest are disclosed. In one arrangement, training data is provided that comprises detected representations of scattered radiation detected by each of plural metrology apparatuses. An encoder encodes each detected representation to provide an encoded representation, and a decoder generates a synthetic detected representation from the respective encoded representation. A classifier estimates from which metrology apparatus originates each encoded representation or each synthetic detected representation. The training data is used to simultaneously perform, in an adversarial relationship relative to each other, a first machine learning process involving the encoder or decoder and a second machine learning process involving the classifier.

公开(公告)号：WO2019201697A1

公开(公告)日：2019-10-24

申请号：PCT/EP2019/059049

申请日：2019-04-10

Applicant: ASML NETHERLANDS B.V.

Inventor： REHMAN, Samee, Ur ,  TSIATMAS, Anagnostis ,  TARABRIN, Sergey ,  VENSELAAR, Joannes, Jitse ,  MEDVEDYEVA, Mariya, Vyacheslavivna ,  ONOSE, Alexandru

IPC: G03F7/20

Abstract: Methods of determining a value of a parameter of interest are disclosed. In one arrangement, a symmetric component and an asymmetric component of a detected pupil representation from illuminating a target are derived. A first metric characterizing the symmetric component and a second metric characterizing the asymmetric component vary non-monotonically as a function of the parameter of interest over a reference range of values of the parameter of interest. A combination of the derived symmetric component and the derived asymmetric component are used to identify a correct value from a plurality of candidate values of the parameter of interest.

公开(公告)号：WO2022144203A1

公开(公告)日：2022-07-07

申请号：PCT/EP2021/086776

申请日：2021-12-20

Applicant: ASML NETHERLANDS B.V.

Inventor： ONOSE, Alexandru ,  TIEMERSMA, Bart, Jacobus, Martinus ,  VERHEUL, Nick ,  DIRKS, Remco

IPC: G06N3/04 ,  G06N3/08 ,  G01B11/00 ,  G03F7/20 ,  H01L21/66 ,  G01B11/02 ,  G01B11/06

Abstract: A modular autoencoder model is described. The modular autoencoder model comprises input models configured to process one or more inputs to a first level of dimensionality suitable for combination with other inputs; a common model configured to: reduce a dimensionality of combined processed inputs to generate low dimensional data in a latent space; and expand the low dimensional data in the latent space into one or more expanded versions of the one or more inputs suitable for generating one or more different outputs; output models configured to use the one or more expanded versions of the one or more inputs to generate the one or more different outputs, the one or more different outputs being approximations of the one or more inputs; and a prediction model configured to estimate one or more parameters based on the low dimensional data in the latent space.

公开(公告)号：WO2020182468A1

公开(公告)日：2020-09-17

申请号：PCT/EP2020/054967

申请日：2020-02-26

Applicant: ASML NETHERLANDS B.V.

Inventor： ONOSE, Alexandru ,  DIRKS, Remco ,  BOSCH, Roger, Hubertus, Elisabeth, Clementine ,  JACOBS, Sander, Silvester, Adelgondus, Marie ,  BUIJNSTERS, Frank, Jaco ,  DE ZWART, Siebe, Tjerk ,  PALHA DA SILVA CLERIGO, Artur ,  VERHEUL, Nick

IPC: G03F7/20

Abstract: Disclosed are a method, computer program and associated apparatuses for metrology. The method includes determining a reconstruction recipe describing at least nominal values for using in a reconstruction of a parameterization describing a target. The method comprises obtaining first measurement data relating to measurements of a plurality of targets on at least one substrate, said measurement data relating to one or more acquisition settings and performing an optimization by minimizing a cost function which minimizes differences between the first measurement data and simulated measurement data based on a reconstructed parameterization for each of said plurality of targets. A constraint on the cost function is imposed based on a hierarchical prior. Also disclosed is a hybrid model for providing simulated data for use in reconstruction, comprising obtaining a coarse model operable to provide simulated coarse data; and training a data driven model to correct said simulated coarse data so as to determine said simulated data.

公开(公告)号：WO2022144205A1

公开(公告)日：2022-07-07

申请号：PCT/EP2021/086783

申请日：2021-12-20

Applicant: ASML NETHERLANDS B.V.

Inventor： TIEMERSMA, Bart, Jacobus, Martinus ,  ONOSE, Alexandru ,  VERHEUL, Nick ,  DIRKS, Remco

IPC: G06N3/04 ,  G06N3/08 ,  G01B11/06 ,  G01B11/02 ,  G01B11/00 ,  G03F7/20 ,  H01L21/66

Abstract: A modular autoencoder model is described. The modular autoencoder model comprises input models configured to process one or more inputs to a first level of dimensionality suitable for combination with other inputs; a common model configured to: reduce a dimensionality of combined processed inputs to generate low dimensional data in a latent space; and expand the low dimensional data in the latent space into one or more expanded versions of the one or more inputs suitable for generating one or more different outputs; output models configured to use the one or more expanded versions of the one or more inputs to generate the one or more different outputs, the one or more different outputs being approximations of the one or more inputs; and a prediction model configured to estimate one or more parameters based on the low dimensional data in the latent space.

公开(公告)号：WO2022144204A1

公开(公告)日：2022-07-07

申请号：PCT/EP2021/086782

申请日：2021-12-20

Applicant: ASML NETHERLANDS B.V.

Inventor： ONOSE, Alexandru ,  TIEMERSMA, Bart, Jacobus, Martinus ,  VERHEUL, Nick ,  DIRKS, Remco ,  BARBIERI, Davide ,  VAN LAARHOVEN, Hendrik, Adriaan

IPC: G06N3/04 ,  G06N3/08 ,  G01B11/00 ,  G03F7/20 ,  H01L21/66 ,  G01B11/02 ,  G01B11/06

Abstract: A modular autoencoder model is described. The modular autoencoder model comprises input models configured to process one or more inputs to a first level of dimensionality suitable for combination with other inputs; a common model configured to: reduce a dimensionality of combined processed inputs to generate low dimensional data in a latent space; and expand the low dimensional data in the latent space into one or more expanded versions of the one or more inputs suitable for generating one or more different outputs; output models configured to use the one or more expanded versions of the one or more inputs to generate the one or more different outputs, the one or more different outputs being approximations of the one or more inputs; and a prediction model configured to estimate one or more parameters based on the low dimensional data in the latent space.

公开(公告)号：WO2019086167A1

公开(公告)日：2019-05-09

申请号：PCT/EP2018/075720

申请日：2018-09-24

Applicant: ASML NETHERLANDS B.V.

Inventor： ONOSE, Alexandru ,  MOSSAVAT, Seyed Iman ,  THEEUWES, Thomas

IPC: G03F7/20

Abstract: Methods and apparatus for estimating an unknown value of at least one of a plurality of sets of data, each set of data comprising a plurality of values indicative of radiation diffracted and/or reflected and/or scattered by one or more features fabricated in or on a substrate, wherein the plurality of sets of data comprises at least one known value, and wherein at least one of the plurality of sets of data comprises an unknown value, the apparatus comprising a processor to estimate the unknown value of the at least one set of data based on: the known values of the plurality of sets of data; a first condition between two or more values within a set of data of the plurality of sets of data; and a second condition between two or more values being part of different sets of data of the plurality of the sets of data.

公开(公告)号：EP4254266A1

公开(公告)日：2023-10-04

申请号：EP22164893.4

申请日：2022-03-29

Applicant: ASML Netherlands B.V.

Inventor： ONOSE, Alexandru ,  VERHEUL, Nick ,  TIEMERSMA, Bart, Jacobus, Martinus ,  CERFONTAINE, Pascal ,  BARBIERI, Davide

IPC: G06N3/04 ,  G06N3/08 ,  G03F7/20

Abstract: A method for ordering and/or selection of latent elements for modeling low dimensional data within a latent space representation, the low dimensional data being a reduced dimensionality representation of input data as determined by a first model component of a model, comprising the steps of training said model and selecting one of said latent element selections based on said training, said training comprising: reducing a dimensionality of the input data to generate said low dimensional data in said latent space representation; training a second model component of said model for each of one or more latent element selections; and optimizing an approximation of the input data as output by said second model component for each said latent element selection, thereby ranking at least one of said plurality of latent elements in the latent space representation based on a contribution of each latent element to the input data.

公开(公告)号：EP4361726A1

公开(公告)日：2024-05-01

申请号：EP22203256.7

申请日：2022-10-24

Applicant: ASML Netherlands B.V.

Inventor： ONOSE, Alexandru ,  MIDDLEBROOKS, Scott, Anderson ,  VERHEUL, Nick ,  VAN KRAAIJ, Markus, Gerardus, Martinus, Maria ,  TIEMERSMA, Bart, Jacobus, Martinus ,  CERFONTAINE, Pascal

IPC: G03F7/20 ,  G06N3/08 ,  G06N20/00

CPC classification number: G03F7/70616 ,  G03F7/70633 ,  G03F7/705 ,  G06N3/08 ,  G06N20/00

Abstract: A method of training an inference model to determine one or more parameters of a product of a fabrication process from measurements of the product. The method comprises obtaining a dataset (DS) of measurements of one or more products of the fabrication process, each of the measurements comprising an array of values obtained by measuring a corresponding one of the products. The method further comprises selecting a proper subset (SS) of the dataset for use in training the inference model, the subset being selected by applying an optimisation procedure to an objective function providing a measure of differences between each measurement in the dataset and corresponding reproduced values of the measurements obtained using a reproduction function having a domain comprising the measurements in the subset and excluding the measurements not in the subset. The method also comprises training the inference model using the proper subset of the dataset.

公开(公告)号：EP3709082A1

公开(公告)日：2020-09-16

申请号：EP19162808.0

申请日：2019-03-14

Applicant: ASML Netherlands B.V.

Inventor： ONOSE, Alexandru ,  DIRKS, Remco ,  BOSCH, Roger, Hubertus, Elisabeth, Clementine ,  JACOBS, Sander, Silvester, Adelgondus, Marie ,  BUIJNSTERS, Frank, Jaco ,  DE ZWART, Siebe, Tjerk ,  PALHA DA SILVA CLERIGO, Artur

IPC: G03F7/20

Abstract: Disclosed are a method, computer program and associated apparatuses for metrology. The method includes determining a reconstruction recipe describing at least nominal values for using in a reconstruction of a parameterization describing a target. The method comprises obtaining first measurement data relating to measurements of a plurality of targets on at least one substrate, said measurement data relating to one or more acquisition settings and solving a cost function minimizing differences between the first measurement data and simulated measurement data based on a reconstructed parameterization for each of said plurality of targets. A constraint on the cost function is imposed based on a hierarchical prior. Also disclosed is a hybrid model for providing simulated data for use in reconstruction, comprising obtaining a coarse model operable to provide simulated coarse data; and training a data driven model to correct said simulated coarse data so as to determine said simulated data.