公开(公告)号：US20200380362A1

公开(公告)日：2020-12-03

申请号：US16970648

申请日：2019-02-20

Applicant: ASML NETHERLANDS B.V.

Inventor： Yu CAO ,  Ya LUO ,  Yen-Wen LU ,  Been-Der CHEN ,  Rafael C. HOWELL ,  Yi ZOU ,  Jing SU ,  Dezheng SUN

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods of training machine learning models related to a patterning process, including a method for training a machine learning model configured to predict a mask pattern. The method including obtaining (i) a process model of a patterning process configured to predict a pattern on a substrate, wherein the process model comprises one or more trained machine learning models, and (ii) a target pattern, and training the machine learning model configured to predict a mask pattern based on the process model and a cost function that determines a difference between the predicted pattern and the target pattern.

公开(公告)号：US20250028298A1

公开(公告)日：2025-01-23

申请号：US18713127

申请日：2022-11-30

Applicant: ASML NETHERLANDS B.V.

Inventor： Duan-Fu Stephen HSU ,  Gerui LIU ,  Wenjie JIN ,  Dezheng SUN

IPC: G05B19/4093

Abstract: Dynamic aberration control in a semiconductor manufacturing process is described. In some embodiments, wavefront data representing a wavefront provided by an optical projection system of a semiconductor processing apparatus may be received. Wavefront drift may be determined based on a comparison of the wavefront data and target wavefront data. Based on the wavefront drift, one or more process parameters may be determined. The one or more process parameters include parameters associated with a thermal device, where the thermal device is configured to provide thermal energy to the optical projection system during operation.

公开(公告)号：US20240319581A1

公开(公告)日：2024-09-26

申请号：US18579176

申请日：2022-07-15

Applicant: ASML NETHERLANDS B.V.

Inventor： Duan-Fu Stephen HSU ,  Jialei TANG ,  Dezheng SUN

IPC: G03F1/36 ,  G03F7/00

CPC classification number: G03F1/36 ,  G03F7/70508 ,  G03F7/706 ,  G03F7/70683 ,  G03F7/706831 ,  G03F7/706837

Abstract: Generating a design (e.g., a metrology mark or a device pattern to be printed on a substrate) that is optimized for aberration sensitivity related to an optical system of a lithography system. A metrology mark (e.g., a transmission image sensor (TIS) mark) is optimized for a given device pattern by matching the aberration sensitivity of the metrology mark with the aberration sensitivity of the device pattern. A cost function that includes the aberration sensitivity difference between the metrology mark and the device pattern is evaluated based on an imaging characteristic response (e.g., a critical dimension (CD) response to focus) obtained from a simulation model that simulates lithography. The cost function is evaluated by modifying the metrology mark until the cost function is minimized and an optimized metrology mark is output when the cost function is minimized.

公开(公告)号：US20220179325A1

公开(公告)日：2022-06-09

申请号：US17436305

申请日：2020-02-20

Applicant: ASML NETHERLANDS B.V.

Inventor： Duan-Fu Stephen HSU ,  Dezheng SUN

IPC: G03F7/20

Abstract: A diffraction pattern guided source mask optimization (SMO) method that includes determining a source variable region from a diffraction pattern. The source variable region corresponds to one or more areas of a diffraction pattern in a pupil for which one or more pupil variables are to be adjusted. The source variable region in the diffraction pattern includes a plurality of pixels in an image of a selected region of interest in the diffraction pattern. Determining the source variable region can include binarization of the plurality of pixels in the image such that individual pixels are either included in the source variable region or excluded from the source variable region. The method can include adjusting the one or more pupil variables for the one or more areas of the pupil that correspond to the source variable region; and rendering a final pupil based on the adjusted one or more pupil variables.