公开(公告)号：WO2019224176A1

公开(公告)日：2019-11-28

申请号：PCT/EP2019/063053

申请日：2019-05-21

Applicant: ASML NETHERLANDS B.V.

Inventor： LI, Danying ,  FAN, Chi-Hsiang ,  ELMALK, Abdalmohsen ,  ZHANG, Youping ,  CHEN, Jay, Jianhui ,  HUANG, Kui-Jun

IPC: G03F7/20

Abstract: Described herein is are method for determining a stack configuration for a substrate subjected a patterning process. The method includes obtaining (i) measurement data of a stack configuration with location information on a printed substrate, (ii) a substrate model configured to predict a stack characteristic based on a location of the substrate, and (iii) a stack map including a plurality of stack configurations based on the substrate model. The method iteratively determines values of model parameters of the substrate model based on a fitting between the measurement data and the plurality of stack configurations of the stack map; and predicts an optimum stack configuration at a particular location based on the substrate model using the values of the model parameters.

公开(公告)号：WO2021063728A1

公开(公告)日：2021-04-08

申请号：PCT/EP2020/076342

申请日：2020-09-22

Applicant: ASML NETHERLANDS B.V.

Inventor： GU, Ning ,  REN, Liping ,  HUANG, Kui-Jun ,  WU, Jian

IPC: G03F7/20

Abstract: A method for monitoring performance of a manufacturing process is described. The method comprises receiving one or more input signals that convey information related to geometry of a substrate generated by the manufacturing process; and determining, with a prediction model, variation in the manufacturing process based on the one or more input signals. A method for predicting substrate geometry associated with a manufacturing process is also described. The method comprises receiving input information including geometry information and manufacturing process information for a substrate; and predicting, using a machine learning prediction model, output substrate geometry based on the input information. The method further comprises tuning the predicted output substrate geometry. The tuning comprises comparing the output substrate geometry to corresponding physical substrate measurements and/or predictions from a different non machine learning prediction model, generating a loss function based on the comparison, and optimizing the loss function.