公开(公告)号：EP4194951A1

公开(公告)日：2023-06-14

申请号：EP21214040.4

申请日：2021-12-13

Applicant: ASML Netherlands B.V.

Inventor： DOUNAEV, Dimitriy ,  GKOROU, Dimitra ,  VAN HERTUM, Pieter ,  LIJFFIJT, Jefrey ,  VAN SHOUBROECK, Joachim Kinley ,  KAREVAN, Zahra ,  YPMA, Alexander

IPC: G03F7/20 ,  G06N20/00

Abstract: A fault in a subject production apparatus which is suspected of being a deviating machine, is identified based on whether it is possible to train a machine learning model to distinguish between first sensor data derived from the subject production apparatus, and second sensor data derived from one or more other production apparatuses which are assumed to be behaving normally. Thus, the discriminative ability of the machine learning model is used as an indicator to discriminate between a faulty machine and the population of healthy machines.

公开(公告)号：EP3935448A1

公开(公告)日：2022-01-12

申请号：EP20703998.3

申请日：2020-02-06

Applicant: ASML Netherlands B.V.

Inventor： LARRANAGA, Maialen ,  GKOROU, Dimitra ,  HASIBI, Faegheh ,  YPMA, Alexander

IPC: G03F7/20 ,  G06N3/04

公开(公告)号：EP3705944A1

公开(公告)日：2020-09-09

申请号：EP19160933.8

申请日：2019-03-06

Applicant: ASML Netherlands B.V.

Inventor： LARRANAGA, Maialen ,  GKOROU, Dimitra ,  HASIBI, Faegheh ,  YPMA, Alexander

IPC: G03F7/20 ,  G06N3/04

Abstract: A method of extracting a feature from a data set includes iteratively extracting a feature 244 from a data set based on a visualization 238 of a residual pattern comprised within the data set, wherein the feature is distinct from a feature extracted in a previous iteration, and the visualization of the residual pattern uses the feature extracted in the previous iteration. Visualizing 234 the data set using the feature extracted in the previous iteration may comprise showing residual patterns of attribute data that are relevant to target data. Visualizing 234 the data set using the feature extracted in the previous iteration may involve adding cluster constraints to the data set, based on the feature extracted in the previous iteration. Additionally or alternatively, visualizing 234 the data set using the feature extracted in the previous iteration may involve defining conditional probabilities conditioned on the feature extracted in the previous iteration.

公开(公告)号：EP4182967A1

公开(公告)日：2023-05-24

申请号：EP21734332.6

申请日：2021-06-21

Applicant: ASML Netherlands B.V.

Inventor： GKOROU, Dimitra ,  BASTANI, Vahid ,  SAHRAEIAN, Reza ,  TABERY, Cyrus, Emil

IPC: H01L21/66 ,  G03F7/20 ,  G05B19/418 ,  G05B23/02

公开(公告)号：EP4116888A1

公开(公告)日：2023-01-11

申请号：EP21184240.6

申请日：2021-07-07

Applicant: ASML Netherlands B.V.

Inventor： VAN HERTUM, Pieter ,  GKOROU, Dimitra ,  VAN SCHOUBROECK, Joachim, Kinley ,  KAREVAN, Zahra ,  YPMA, Alexander

IPC: G06N5/04 ,  G06N7/00 ,  G03F7/20 ,  G05B23/02

Abstract: A computer implemented method for diagnosing a system comprising a plurality of modules. The method comprises: receiving a causal graph, the causal graph defining (i) a plurality of nodes each representing a module of the system , wherein each module is characterized by one or more signals; and (ii) edges connected between the nodes, the edges representing propagation of performance between modules; generating a reasoning tool by augmenting the causal graph with diagnostics knowledge based on historically determined relations between performance, statistical and causal characteristics of at least one module out of the plurality of modules; obtaining a health metric of the at least one module, wherein the health metric is associated with the one or more signals associated with the at least one module; and using the health metric as an input to the reasoning tool to identify a module that is the most likely cause of the behaviour.

公开(公告)号：EP3767392A1

公开(公告)日：2021-01-20

申请号：EP19186833.0

申请日：2019-07-17

Applicant: ASML Netherlands B.V.

Inventor： BASTANI, Vahid ,  SONNTAG, DAG ,  SAHRAEIAN, Reza ,  GKOROU, Dimitra

IPC: G03F7/20 ,  G05B19/418 ,  H01L21/66

Abstract: A method of determining the contribution of a process feature to the performance of a process of patterning substrates. The method may comprise obtaining (402) a first model trained on first process data and first performance data. One or more substrates may be identified (404) based on a quality of prediction of the first model when applied to process data associated with the one or more substrates. A second model may be trained (406) on second process data and second performance data associated with the identified one or more substrates. The second model may be used (408) to determine the contribution of a process feature of the second process data to the second performance data associated with the one or more substrates.

公开(公告)号：EP3352013A1

公开(公告)日：2018-07-25

申请号：EP17152659.3

申请日：2017-01-23

Applicant: ASML Netherlands B.V.

Inventor： YPMA, Alexander ,  GKOROU, Dimitra ,  TSIROGIANNIS, Georgios ,  HOOGENBOOM, Thomas, Leo, Maria ,  VAN HAREN, Richard, Johannes, Franciscus

IPC: G03F7/20 ,  G05B19/418 ,  H01L21/66

CPC classification number: G03F7/705 ,  G03F7/70525 ,  G03F7/70616 ,  G03F7/70625 ,  G03F7/70633 ,  G05B19/41875 ,  G05B2219/32194 ,  G05B2219/45028 ,  G05B2219/45031 ,  H01L22/10 ,  H01L22/12 ,  H01L22/20 ,  Y02P90/22

Abstract: The invention generates predicted data for control or monitoring of a production process to improve a parameter of interest. Context data 502 associated with operation of the production process 504 is obtained. Metrology/test 508 is performed on the product 506 of the production process 504, thereby obtaining performance data 510. A context-to-performance model is provided to generate predicted performance data 526 based on labeling of the context data 502 with performance data. This is an instance of semi-supervised learning. The context-to-performance model includes the learner 522 that performs semi-supervised labeling. The context-to-performance model is modified using prediction information related to quality of the context data and/or performance data. Prediction information may comprise relevance information relating to relevance of the obtained context data and/or obtained performance data to the parameter of interest. The prediction information may comprise model uncertainty information relating to uncertainty of the predicted performance data.

公开(公告)号：EP3994525A1

公开(公告)日：2022-05-11

申请号：EP20730276.1

申请日：2020-06-05

Applicant: ASML Netherlands B.V.

Inventor： BASTANI, Vahid ,  SONNTAG, Dag ,  SAHRAEIAN, Reza ,  GKOROU, Dimitra

IPC: G03F7/20 ,  G05B19/418 ,  H01L21/66

公开(公告)号：EP3945548A1

公开(公告)日：2022-02-02

申请号：EP20188698.3

申请日：2020-07-30

Applicant: ASML Netherlands B.V.

Inventor： GKOROU, Dimitra ,  BASTANI, Vahid ,  SAHRAEIAN, Reza ,  TABERY, Cyrus, Emil

IPC: H01L21/66 ,  G03F7/20 ,  G05B19/418 ,  G05B23/02

Abstract: Methods and apparatus for classifying semiconductor wafers. The method comprises: sorting a set of semiconductor wafers, using a model, into a plurality of sub-sets based on parameter data corresponding to one or more parameters of the set of semiconductor wafers, wherein the parameter data for semiconductor wafers in a sub-set include one or more common characteristics; identifying one or more semiconductor wafers within a sub-set based on a probability of the one or more semiconductor wafers being correctly allocated to the sub-set; comparing the parameter data of the one or more identified semiconductor wafers to reference parameter data; and reconfiguring the model based on the comparison. The comparison is undertaken by a human to provide constraints for the model. The apparatus is configured to undertake the method.

公开(公告)号：EP3913435A1

公开(公告)日：2021-11-24

申请号：EP20175361.3

申请日：2020-05-19

Applicant: ASML Netherlands B.V.

Inventor： SAHRAEIAN, Reza ,  BASTANI, Vahid ,  GKOROU, Dimitra ,  DOS SANTOS GUZELLA, Thiago

IPC: G03F7/20 ,  G06N5/04

Abstract: Apparatus and methods of configuring an imputer model for imputing a second parameter. The method comprises inputting a first data set comprising values of a first parameter to the imputer model, and evaluating the imputer model to obtain a second data set comprising imputed values of the second parameter. The method further comprises obtaining a third data set comprising measured values of a third parameter, wherein the third parameter is correlated to the second parameter; obtaining a prediction model configured to infer values of the third parameter based on inputting values of the second parameter; inputting the second data set to the prediction model, and evaluating the prediction model to obtain inferred values of the third parameter; and configuring the imputer model based on a comparison of the inferred values and the measured values of the third parameter.