COMPUTATIONAL METROLOGY BASED SAMPLING SCHEME

    公开(公告)号:US20200371441A1

    公开(公告)日:2020-11-26

    申请号:US16959736

    申请日:2018-12-17

    Abstract: A method for generating metrology sampling scheme for a patterning process, the method including: obtaining a parameter map of a parameter of a patterning process for a substrate; decomposing the parameter map to generate a fingerprint specific to an apparatus of the patterning process and/or a combination of apparatuses of the patterning process; and based on the fingerprint, generating a metrology sampling scheme for a subsequent substrate at the apparatus of the patterning process and/or the combination of apparatuses of the patterning process, wherein the sampling scheme is configured to distribute sampling points on the subsequent substrate so as to improve a metrology sampling density.

    CAUSAL CONVOLUTION NETWORK FOR PROCESS CONTROL

    公开(公告)号:US20240184254A1

    公开(公告)日:2024-06-06

    申请号:US18287613

    申请日:2022-04-19

    CPC classification number: G05B13/027 G03F7/705 G03F7/70525

    Abstract: A method for configuring a semiconductor manufacturing process, the method comprising: obtaining a plurality of first values of a first parameter based on successive measurements associated with a first operation of a process step in the semiconductor manufacturing process; using a causal convolutional neural network to determine a predicted value of a second parameter based on the first values; and using the predicted value of the second parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

    DETERMINING A CORRECTION TO A PROCESS

    公开(公告)号:US20210333785A1

    公开(公告)日:2021-10-28

    申请号:US17367901

    申请日:2021-07-06

    Abstract: A method for configuring a semiconductor manufacturing process, the method including: obtaining a first value of a first parameter based on measurements associated with a first operation of a process step in the semiconductor manufacturing process and a first sampling scheme; using a recurrent neural network to determine a predicted value of the first parameter based on the first value; and using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

Patent Agency Ranking