DETECTING AND CORRECTING SUBSTRATE PROCESS DRIFT USING MACHINE LEARNING

    公开(公告)号:US20220066411A1

    公开(公告)日:2022-03-03

    申请号:US17379728

    申请日:2021-07-19

    Abstract: Methods and systems for detecting and correcting substrate process drift using machine learning are provided. Data associated with processing each of a first set of substrates at a manufacturing system according to a process recipe is provided as input to a trained machine learning model. One or more outputs are obtained from the trained machine learning model. An amount of drift of a first set of metrology measurement values for the first set of substrates from a target metrology measurement value is determined from the one or more outputs. Process recipe modification identifying one or more modifications to the process recipe is also determined. For each modification, an indication of a level of confidence that a respective modification to the process recipe satisfies a drift criterion for a second set of substrates is determined. In response to an identification of the respective modification with a level of confidence that satisfies a level of confidence criterion, the process recipe is updated based on the respective modification.

    ON-THE-FLY MEASUREMENT OF SUBSTRATE STRUCTURES

    公开(公告)号:US20240321649A1

    公开(公告)日:2024-09-26

    申请号:US18611531

    申请日:2024-03-20

    CPC classification number: H01L22/12 G01N21/41 G01N21/9501

    Abstract: A method includes determining a plurality of measurement targets of a substrate. The substrate includes a plurality of structures. Each measurement target is associated with a structure of the plurality of structures. The method further includes operating one or more motors to cause motion of a substrate support to dispose a first measurement target within a field of view of a measurement instrument. The method further includes causing the measurement instrument to take a first measurement of the first measurement target as the first measurement target passes through the field of view of the measurement instrument. The method further includes operating the one or more motors of the substrate support to dispose a second measurement target of the substrate within the field of view of the measurement instrument.

    INTEGRATED SUBSTRATE MEASUREMENT SYSTEM
    5.
    发明公开

    公开(公告)号:US20230238266A1

    公开(公告)日:2023-07-27

    申请号:US17584322

    申请日:2022-01-25

    Abstract: An apparatus includes a substrate holder, a first actuator to rotate the substrate holder, a second actuator to move the substrate holder linearly, a first sensor to generate one or more first measurements or images of the substrate, a second sensor to generate one or more second measurements of target positions on the substrate, and a processing device. The processing device estimates a position of the substrate on the substrate holder and causes the first actuator to rotate the substrate holder about a first axis. The rotation causes an offset between a field of view of the second sensor and a target position on the substrate due to the substrate not being centered on the substrate holder. The processing device causes the second actuator to move the substrate holder linearly along a second axis to correct the offset. The processing device determines a profile across a surface of the substrate based on the one or more second measurements of the target positions.

    DETERMINING SUBSTRATE PROFILE PROPERTIES USING MACHINE LEARNING

    公开(公告)号:US20230062206A1

    公开(公告)日:2023-03-02

    申请号:US18046872

    申请日:2022-10-14

    Abstract: Spectral data associated with a first prior substrate and/or a second prior substrate is obtained. A metrology measurement value associated with the first portion of the first prior substrate is determined based on one or more metrology measurement values measured for at least one of a second portion of the first prior substrate or a third portion of a second prior substrate. Training data for training a machine learning model to predict metrology measurement values of a current substrate is generated. Generating the training data includes generating a first training input including the spectral data associated with the first prior substrate and generating a first target output for the first training input, the first target output including the determined metrology measurement value associated with the first portion of the first prior substrate. The training data is provided to train the machine learning model.

    VIBRATION DETERMINATION IN SUBSTRATE PROCESSING SYSTEMS

    公开(公告)号:US20240393761A1

    公开(公告)日:2024-11-28

    申请号:US18324080

    申请日:2023-05-25

    Abstract: A method includes receiving, by a processing device, position error data from one or more motors of a process chamber. The method further includes performing preprocessing of the position error data. The method further includes transforming the position error data to a frequency domain. The method further includes determining, based on the frequency domain position error data, that a vibration fault has occurred in connection with the process chamber. The method further includes performing a corrective action in view of the vibration fault.

Patent Agency Ranking