公开(公告)号：US20220299881A1

公开(公告)日：2022-09-22

申请号：US17636103

申请日：2020-08-01

Applicant: ASML NETHERLANDS B.V.

Inventor： Yunan ZHENG ,  Yongfa FAN ,  Mu FENG ,  Leiwu ZHENG ,  Jen-Shiang WANG ,  Ya LUO ,  Chenji ZHANG ,  Jun CHEN ,  Zhenyu HOU ,  Jinze WANG ,  Feng CHEN ,  Ziyang MA ,  Xin GUO ,  Jin CHENG

IPC: G03F7/20

Abstract: A method for generating modified contours and/or generating metrology gauges based on the modified contours. A method of generating metrology gauges for measuring a physical characteristic of a structure on a substrate includes obtaining (i) measured data associated with the physical characteristic of the structure printed on the substrate, and (ii) at least portion of a simulated contour of the structure, the at least a portion of the simulated contour being associated with the measured data; modifying, based on the measured data, the at least a portion of the simulated contour of the structure; and generating the metrology gauges on or adjacent to the modified at least a portion of the simulated contour, the metrology gauges being placed to measure the physical characteristic of the simulated contour of the structure.

公开(公告)号：US20220179321A1

公开(公告)日：2022-06-09

申请号：US17442662

申请日：2020-03-05

Applicant: ASML NETHERLANDS B.V.

Inventor： Ziyang MA ,  Jin CHENG ,  Ya LUO ,  Leiwu ZHENG ,  Xin GUO ,  Jen-Shiang WANG ,  Yongfa FAN ,  Feng CHEN ,  Yi-Yin CHEN ,  Chenji ZHANG ,  Yen- Wen LU

IPC: G03F7/20 ,  G06N3/08 ,  G06T7/00

Abstract: A method for training a patterning process model, the patterning process model configured to predict a pattern that will be formed by a patterning process. The method involves obtaining an image data associated with a desired pattern, a measured pattern of the substrate, a first model including a first set of parameters, and a machine learning model including a second set of parameters; and iteratively determining values of the first set of parameters and the second set of parameters to train the patterning process model. An iteration involves executing, using the image data, the first model and the machine learning model to cooperatively predict a printed pattern of the substrate; and modifying the values of the first set of parameters and the second set of parameters such that a difference between the measured pattern and the predicted pattern is reduced.

公开(公告)号：US20250021015A1

公开(公告)日：2025-01-16

申请号：US18705509

申请日：2022-10-26

Applicant: ASML NETHERLANDS B.V.

Inventor： Jin CHENG ,  Feng CHEN ,  Leiwu ZHENG ,  Yongfa FAN ,  Yen-Wen LU ,  Jen-Shiang WANG ,  Ziyang MA ,  Dianwen ZHU ,  Xi CHEN ,  Yu ZHAO

IPC: G03F7/00 ,  G03F1/36 ,  G03F1/70

Abstract: An etch bias direction is determined based on a curvature of a contour in a substrate pattern. The etch bias direction is configured to be used to enhance an accuracy of a semiconductor patterning process relative to prior patterning processes. In some embodiments, a representation of the substrate pattern is received, which includes the contour in the substrate pattern. The curvature of the contour of the substrate pattern is determined, and an etch bias direction is determined based on the curvature by considering curvatures of adjacent contour portions. A simulation model is used to determine an etch effect based on the etch bias direction for an etching process on the substrate pattern.

公开(公告)号：US20220284344A1

公开(公告)日：2022-09-08

申请号：US17631557

申请日：2020-07-30

Applicant: ASML NETHERLANDS B.V.

Inventor： Ziyang MA ,  Jin CHENG ,  Ya LUO ,  Leiwu ZHENG ,  Xin GUO ,  Jen-Shiang WANG

IPC: G06N20/00

Abstract: A method for training a machine learning model configured to predict values of a physical characteristic associated with a substrate and for use in adjusting a patterning process. The method involves obtaining a reference image; determining a first set of model parameter values of the machine learning model such that a first cost function is reduced from an initial value of the cost function obtained using an initial set of model parameter values, where the first cost function is a difference between the reference image and an image generated via the machine learning model; and training, using the first set of model parameter values, the machine learning model such that a combination of the first cost function and a second cost function is iteratively reduced, the second cost function representing a difference between measured values and predicted values.