公开(公告)号：US20220138921A1

公开(公告)日：2022-05-05

申请号：US17089158

申请日：2020-11-04

Applicant: Tokyo Electron Limited

Inventor： Shin-Yee LU ,  Ivan MALEEV

IPC: G06T7/00 ,  G06T5/40 ,  G06T5/20 ,  G06N3/08

Abstract: A method for detecting defects on a sample based on a defect inspection apparatus is provided. In the method, an image data set that includes defect data and non-defect data is organized. A convolutional neural network (CNN) model is defined. The CNN model is trained based on the image data set. The defects on the sample are detected based on inspection data of the defect inspection apparatus and the CNN model. The sample includes uniformly repeating structures, and the inspection data of the defect inspection apparatus is generated by filtering out signals of the uniformly repeating structures of the sample.

公开(公告)号：US20230057763A1

公开(公告)日：2023-02-23

申请号：US17889077

申请日：2022-08-16

Applicant: Tokyo Electron Limited

Inventor： Ivan MALEEV ,  Shin-Yee LU ,  Dimitri KLYACHKO ,  Ching Ling MENG ,  Xinkang TIAN

IPC: H01L21/68 ,  H01J37/32 ,  H01L21/677

Abstract: A semiconductor processing system includes a processing chamber configured to perform a semiconductor manufacturing process on each of a plurality of wafers. The processing chamber includes at least one consumable component, and a substrate handling module located proximate the processing chamber and in communication with the processing chamber via a wafer access port. The wafer handling module includes a wafer handling robot configured to transfer each of the wafers between to the substrate handling module and the processing chamber through the wafer access port, and an optical diagnostic system including an optical sensor configured to detect an optical signal from the at least one consumable component. A controller is configured to cause the processing chamber to perform the semiconductor manufacturing process on each respective wafer and to cause the optical diagnostic system to detect the optical signal during a time when the processing chamber is not performing the semiconductor manufacturing process on the wafers.

公开(公告)号：US20230274413A1

公开(公告)日：2023-08-31

申请号：US18143949

申请日：2023-05-05

Applicant: Tokyo Electron Limited

Inventor： Shin-Yee LU ,  Ivan MALEEV

IPC: G06T7/00 ,  G06T5/40 ,  G06T5/20 ,  G06N3/08

CPC classification number: G06T7/001 ,  G06T5/40 ,  G06T5/20 ,  G06N3/08 ,  G06T2207/20061 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06T2207/30148

Abstract: A method for detecting defects on a sample based on a defect inspection apparatus is provided. In the method, an image data set that includes defect data and non-defect data is organized. A convolutional neural network (CNN) model is defined. The CNN model is trained based on the image data set. The defects on the sample are detected based on inspection data of the defect inspection apparatus and the CNN model. The sample includes uniformly repeating structures, and the inspection data of the defect inspection apparatus is generated by filtering out signals of the uniformly repeating structures of the sample.

公开(公告)号：US20230055839A1

公开(公告)日：2023-02-23

申请号：US17889114

申请日：2022-08-16

Applicant: Tokyo Electron Limited

Inventor： Ivan MALEEV ,  Shin-Yee LU ,  Dimitri KLYACHKO ,  Ching Ling MENG ,  Xinkang TIAN

IPC: H01L21/68 ,  H01J37/32 ,  H01L21/677

Abstract: A method of manufacturing semiconductor devices includes repeatedly performing a transfer operation which transfers each of a plurality of semiconductor wafers between a substrate handling module and a processing chamber through a wafer access port, the processing chamber including at least one consumable component. Using the processing chamber, a semiconductor manufacturing process is performed on each of the plurality of semiconductor wafers; and detecting an optical signal from the at least one consumable component during a time when the processing chamber is not performing the semiconductor manufacturing process on the wafers.