公开(公告)号：US20210150696A1

公开(公告)日：2021-05-20

申请号：US16687349

申请日：2019-11-18

Applicant: STMICROELECTRONICS (ROUSSET) SAS

Inventor： Laurent BIDAULT

IPC: G06T7/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A device includes image generation circuitry and convolutional-neural-network circuitry. The image generation circuitry, in operation, generates a digital image representation of a wafer defect map (WDM). The convolutional-neural-network circuitry, in operation, generates a defect classification associated with the WDM based on: the digital image representation of the WDM and a data-driven model associating WDM images with classes of a defined set of classes of wafer defects and generated using a training data set augmented based on defect pattern orientation types associated with training images.

公开(公告)号：US20230044794A1

公开(公告)日：2023-02-09

申请号：US17962014

申请日：2022-10-07

Applicant: STMICROELECTRONICS (ROUSSET) SAS

Inventor： Laurent BIDAULT

IPC: G06T7/00 ,  G06N3/04

Abstract: A device includes image generation circuitry and convolutional-neural-network circuitry. The image generation circuitry, in operation, generates a digital image representation of a wafer defect map (WDM). The convolutional-neural-network circuitry, in operation, generates a defect classification associated with the WDM based on the digital image representation of the WDM and a data-driven model generated using an artificial wafer defect digital image (AWDI) data set and associating AWDIs with classes of a defined set of classes of wafer defects. A wafer manufacturing process may be controlled based on the classifications of WDMs.

公开(公告)号：US20210150688A1

公开(公告)日：2021-05-20

申请号：US16687345

申请日：2019-11-18

Applicant: STMICROELECTRONICS (ROUSSET) SAS

Inventor： Laurent BIDAULT

IPC: G06T7/00 ,  G06N3/04

Abstract: A device includes image generation circuitry and convolutional-neural-network circuitry. The image generation circuitry, in operation, generates a digital image representation of a wafer defect map (WDM). The convolutional-neural-network circuitry, in operation, generates a defect classification associated with the WDM based on the digital image representation of the WDM and a data-driven model generated using an artificial wafer defect digital image (AWDI) data set and associating AWDIs with classes of a defined set of classes of wafer defects. A wafer manufacturing process may be controlled based on the classifications of WDMs.

公开(公告)号：US20220067916A1

公开(公告)日：2022-03-03

申请号：US17522541

申请日：2021-11-09

Applicant: STMICROELECTRONICS (ROUSSET) SAS

Inventor： Laurent BIDAULT

IPC: G06T7/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A device includes image generation circuitry and convolutional-neural-network circuitry. The image generation circuitry, in operation, generates a digital image representation of a wafer defect map (WDM). The convolutional-neural-network circuitry, in operation, generates a defect classification associated with the WDM based on: the digital image representation of the WDM and a data-driven model associating WDM images with classes of a defined set of classes of wafer defects and generated using a training data set augmented based on defect pattern orientation types associated with training images.