MOTION CONTROL USING AN ARTIFICIAL NEURAL NETWORK

    公开(公告)号:US20230315027A1

    公开(公告)日:2023-10-05

    申请号:US18013154

    申请日:2021-06-17

    CPC classification number: G05B13/027 G03F7/706841 G06N3/084

    Abstract: Variable setpoints and/or other factors may limit iterative learning control for moving components of an apparatus. The present disclosure describes a processor configured to control movement of a component of an apparatus with at least one prescribed movement. The processor is configured to receive a control input such as and/or including a variable setpoint. The control input indicates the at least one prescribed movement for the component. The processor is configured to determine, with a trained artificial neural network, based on the control input, a feedforward output for the component. The artificial neural network is pretrained with a training data set such that the artificial neural network determines the output regardless of whether or not the control input falls outside the training data set. The processor controls the component based on at least the output.

    METHOD OF DETERMINING A PROPERTY OF A STRUCTURE, INSPECTION APPARATUS AND DEVICE MANUFACTURING METHOD

    公开(公告)号:US20190361360A1

    公开(公告)日:2019-11-28

    申请号:US16331601

    申请日:2017-08-17

    Abstract: An optical system and detector capture a distribution of radiation modified by interaction with a target structure. The observed distribution is used to calculate a property of the structure (e.g. CD or overlay). A condition error (e.g. focus error) associated with the optical system is variable between observations. The actual condition error specific to each capture is recorded and used to apply a correction for a deviation of the observed distribution due to the condition error specific to the observation. The correction in one practical example is based on a unit correction previously defined with respect to a unit focus error. This unit correction can be scaled linearly, in accordance with a focus error specific to the observation.

Patent Agency Ranking