-
公开(公告)号:US11577356B2
公开(公告)日:2023-02-14
申请号:US16554427
申请日:2019-08-28
发明人: Benjamin Cherian , Jun Qian , Nicholas Wiswell , Dominic J. Benvegnu , Boguslaw A. Swedek , Thomas H. Osterheld
IPC分类号: G06N3/02 , B24B37/013 , G06N3/084
摘要: During chemical mechanical polishing of a substrate, a signal value that depends on a thickness of a layer in a measurement spot on a substrate undergoing polishing is determined by a first in-situ monitoring system. An image of at least the measurement spot of the substrate is generated by a second in-situ imaging system. Machine vision processing, e.g., a convolutional neural network, is used to determine a characterizing value for the measurement spot based on the image. Then a measurement value is calculated based on both the characterizing value and the signal value.
-
公开(公告)号:US20190283204A1
公开(公告)日:2019-09-19
申请号:US16351954
申请日:2019-03-13
发明人: Boguslaw A. Swedek , Dominic J. Benvegnu , Chih Chung Chou , Nicholas Wiswell , Thomas H. Osterheld , Jeonghoon Oh
IPC分类号: B24B37/013 , B24B49/12 , B24B37/04 , H01L21/66
摘要: A chemical mechanical polishing apparatus includes a platen to support a polishing pad, the platen having a recess, a flexible membrane in the recess, and an in-situ vibration monitoring system to generate a signal. The in-situ acoustic monitoring system includes a vibration sensor supported by the flexible membrane and positioned to couple to an underside of the polishing pad.
-
公开(公告)号:US11507824B2
公开(公告)日:2022-11-22
申请号:US16449183
申请日:2019-06-21
IPC分类号: G06N3/08 , G05B13/02 , G05B19/4063 , G05B19/4155 , G06N3/04 , H01L21/66
摘要: A method of generating training spectra for training of a neural network includes generating a plurality of theoretically generated initial spectra from an optical model, sending the plurality of theoretically generated initial spectra to a feedforward neural network to generate a plurality of modified theoretically generated spectra, sending an output of the feedforward neural network and empirically collected spectra to a discriminatory convolutional neural network, determining that the discriminatory convolutional neural network does not discriminate between the modified theoretically generated spectra and empirically collected spectra, and thereafter, generating a plurality of training spectra from the feedforward neural network.
-
公开(公告)号:US20200094370A1
公开(公告)日:2020-03-26
申请号:US16554427
申请日:2019-08-28
发明人: Benjamin Cherian , Jun Qian , Nicholas Wiswell , Dominic J. Benvegnu , Boguslaw A. Swedek , Thomas H. Osterheld
IPC分类号: B24B37/013 , G06N3/08
摘要: During chemical mechanical polishing of a substrate, a signal value that depends on a thickness of a layer in a measurement spot on a substrate undergoing polishing is determined by a first in-situ monitoring system. An image of at least the measurement spot of the substrate is generated by a second in-situ imaging system. Machine vision processing, e.g., a convolutional neural network, is used to determine a characterizing value for the measurement spot based on the image. Then a measurement value is calculated based on both the characterizing value and the signal value.
-
-
-