METHOD FOR PREDICTING STOCHASTIC CONTRIBUTORS

    公开(公告)号:US20230081821A1

    公开(公告)日:2023-03-16

    申请号:US17986829

    申请日:2022-11-14

    Abstract: Described herein is a method for training a machine learning model to determine a source of error contribution to multiple features of a pattern printed on a substrate. The method includes obtaining training data having multiple datasets, wherein each dataset has error contribution values representative of an error contribution from one of multiple sources to the features, and wherein each dataset is associated with an actual classification that identifies a source of the error contribution of the corresponding dataset; and training, based on the training data, a machine learning model to predict a classification of a reference dataset of the datasets such that a cost function that determines a difference between the predicted classification and the actual classification of the reference dataset is reduced.

    PROCESS WINDOW BASED ON DEFECT PROBABILITY

    公开(公告)号:US20210356874A1

    公开(公告)日:2021-11-18

    申请号:US17389842

    申请日:2021-07-30

    Abstract: A method including obtaining (i) measurements of a parameter of the feature, (ii) data related to a process variable of a patterning process, (iii) a functional behavior of the parameter defined as a function of the process variable based on the measurements of the parameter and the data related to the process variable, (iv) measurements of a failure rate of the feature, and (v) a probability density function of the process variable for a setting of the process variable, converting the probability density function of the process variable to a probability density function of the parameter based on a conversion function, where the conversion function is determined based on the function of the process variable, and determining a parameter limit of the parameter based on the probability density function of the parameter and the measurements of the failure rate.

    PROCESS WINDOW BASED ON DEFECT PROBABILITY

    公开(公告)号:US20210018850A1

    公开(公告)日:2021-01-21

    申请号:US16955483

    申请日:2018-12-17

    Abstract: A method including obtaining (i) measurements of a parameter of the feature, (ii) data related to a process variable of a patterning process, (iii) a functional behavior of the parameter defined as a function of the process variable based on the measurements of the parameter and the data related to the process variable, (iv) measurements of a failure rate of the feature, and (v) a probability density function of the process variable for a setting of the process variable, converting the probability density function of the process variable to a probability density function of the parameter based on a conversion function, where the conversion function is determined based on the function of the process variable, and determining a parameter limit of the parameter based on the probability density function of the parameter and the measurements of the failure rate.

    PROCESS WINDOW BASED ON DEFECT PROBABILITY
    7.
    发明公开

    公开(公告)号:US20240126181A1

    公开(公告)日:2024-04-18

    申请号:US18511454

    申请日:2023-11-16

    CPC classification number: G03F7/70633 G03F7/705 G03F7/70558 G03F7/70625

    Abstract: A method including obtaining (i) measurements of a parameter of the feature, (ii) data related to a process variable of a patterning process, (iii) a functional behavior of the parameter defined as a function of the process variable based on the measurements of the parameter and the data related to the process variable, (iv) measurements of a failure rate of the feature, and (v) a probability density function of the process variable for a setting of the process variable, converting the probability density function of the process variable to a probability density function of the parameter based on a conversion function, where the conversion function is determined based on the function of the process variable, and determining a parameter limit of the parameter based on the probability density function of the parameter and the measurements of the failure rate.

Patent Agency Ranking