公开(公告)号：US20230236512A1

公开(公告)日：2023-07-27

申请号：US18118695

申请日：2023-03-07

Applicant: ASML NETHERLANDS B.V.

Inventor： Youping ZHANG ,  Maxime Philippe Frederic Genin ,  Cong Wu ,  Jing Su ,  Weixuan Hu ,  Yi Zou

IPC: G03F7/20

CPC classification number: G03F7/705 ,  G03F7/70675

Abstract: Methods for training a process model and determining ranking of simulated patterns (e.g., corresponding to hot spots). A method involves obtaining a training data set including: (i) a simulated pattern associated with a mask pattern to be printed on a substrate, (ii) inspection data of a printed pattern imaged on the substrate using the mask pattern, and (iii) measured values of a parameter of the patterning process applied during imaging of the mask pattern on the substrate; and training a machine learning model for the patterning process based on the training data set to predict a difference in a characteristic of the simulated pattern and the printed pattern. The trained machine learning model can be used for determining a ranking of hot spots. In another method a model is trained based on measurement data to predict ranking of the hot spots.

公开(公告)号：US11635699B2

公开(公告)日：2023-04-25

申请号：US17312709

申请日：2019-12-04

Applicant: ASML NETHERLANDS B.V.

Inventor： Youping Zhang ,  Maxime Philippe Frederic Genin ,  Cong Wu ,  Jing Su ,  Weixuan Hu ,  Yi Zou

IPC: G03F7/20

Abstract: Methods for training a process model and determining ranking of simulated patterns (e.g., corresponding to hot spots). A method involves obtaining a training data set including: (i) a simulated pattern associated with a mask pattern to be printed on a substrate, (ii) inspection data of a printed pattern imaged on the substrate using the mask pattern, and (iii) measured values of a parameter of the patterning process applied during imaging of the mask pattern on the substrate; and training a machine learning model for the patterning process based on the training data set to predict a difference in a characteristic of the simulated pattern and the printed pattern. The trained machine learning model can be used for determining a ranking of hot spots. In another method a model is trained based on measurement data to predict ranking of the hot spots.

公开(公告)号：US12242201B2

公开(公告)日：2025-03-04

申请号：US17276533

申请日：2019-09-20

Applicant: ASML NETHERLANDS B.V.

Inventor： Youping Zhang ,  Weixuan Hu ,  Fei Yan ,  Wei Peng ,  Vivek Kumar Jain

IPC: G03F7/00

Abstract: A method of hot spot ranking for a patterning process. The method includes obtaining (i) a set of hot spots of a patterning process, (ii) measured values of one or more parameters of the patterning process corresponding to the set of hot spots, and (ii) simulated values of the one or more parameters of the patterning process corresponding to the set of hot spots; determining a measurement feedback based on the measured values and the simulated values of the one or more parameters of the patterning process; and determining, via simulation of a process model of the patterning process, a ranking of a hot spot within the set of hot spots based on the measurement feedback.

公开(公告)号：US12038694B2

公开(公告)日：2024-07-16

申请号：US18118695

申请日：2023-03-07

Applicant: ASML NETHERLANDS B.V.

Inventor： Youping Zhang ,  Maxime Philippe Frederic Genin ,  Cong Wu ,  Jing Su ,  Weixuan Hu ,  Yi Zou

IPC: G03F7/00

CPC classification number: G03F7/705 ,  G03F7/70675

Abstract: Methods for training a process model and determining ranking of simulated patterns (e.g., corresponding to hot spots). A method involves obtaining a training data set including: (i) a simulated pattern associated with a mask pattern to be printed on a substrate, (ii) inspection data of a printed pattern imaged on the substrate using the mask pattern, and (iii) measured values of a parameter of the patterning process applied during imaging of the mask pattern on the substrate; and training a machine learning model for the patterning process based on the training data set to predict a difference in a characteristic of the simulated pattern and the printed pattern. The trained machine learning model can be used for determining a ranking of hot spots. In another method a model is trained based on measurement data to predict ranking of the hot spots.