Generating predicted data for control or monitoring of a production process

    公开(公告)号:US11099486B2

    公开(公告)日:2021-08-24

    申请号:US16477619

    申请日:2017-12-13

    IPC分类号: G03F7/20 G05B19/418 H01L21/66

    摘要: A technique to generate predicted data for control or monitoring of a production process to improve a parameter of interest. Context data associated with operation of the production process is obtained. Metrology/testing is performed on the product of the production process, thereby obtaining performance data. A context-to-performance model is provided to generate predicted performance data based on labeling of the context data with performance data. This is an instance of semi-supervised learning. The context-to-performance model may include the learner that performs semi-supervised labeling. The context-to-performance model is modified using prediction information related to quality of the context data and/or performance data. Prediction information may include relevance information relating to relevance of the obtained context data and/or obtained performance data to the parameter of interest. The prediction information may include model uncertainty information relating to uncertainty of the predicted performance data.

    Maintaining a set of process fingerprints

    公开(公告)号:US11099485B2

    公开(公告)日:2021-08-24

    申请号:US16493326

    申请日:2018-04-09

    IPC分类号: G03F7/20 G03F9/00

    摘要: A method of maintaining a set of fingerprints representing variation of one or more process parameters across wafers subjected to a device manufacturing method, the method including: receiving measurement data of one or more parameters measured on wafers; updating the set of fingerprints based on an expected evolution of the one or more process parameters; and evaluation of the updated set of fingerprints based on decomposition of the received measurement data in terms of the updated set of fingerprints. Each fingerprint may have a stored likelihood of occurrence, and the decomposition may involve: estimating, based the received measurement data, likelihoods of occurrence of the set of fingerprints in the received measurement data; and updating the stored likelihoods of occurrence based on the estimated likelihoods.