公开(公告)号：US20180197714A1

公开(公告)日：2018-07-12

申请号：US15835399

申请日：2017-12-07

Applicant: KLA-Tencor Corporation

Inventor： Martin Plihal ,  Erfan Soltanmohammadi ,  Saravanan Paramasivam ,  Sairam Ravu ,  Ankit Jain ,  Prasanti Uppaluri ,  Vijay Ramachandran

IPC: H01J37/22 ,  G01N23/04 ,  H01J37/28 ,  H01L21/67

CPC classification number: H01J37/222 ,  G01N23/04 ,  G05B19/41875 ,  G05B2219/32186 ,  G05B2219/32196 ,  H01J37/28 ,  H01J2237/22 ,  H01J2237/2817 ,  H01L21/67288

Abstract: Wafer inspection with stable nuisance rates and defect of interest capture rates are disclosed. This technique can be used for discovery of newly appearing defects that occur during the manufacturing process. Based on a first wafer, defects of interest are identified based on the classified filtered inspection results. For each remaining wafer, the defect classifier is updated and defects of interest in the next wafer are identified based on the classified filtered inspection results.

公开(公告)号：US11237119B2

公开(公告)日：2022-02-01

申请号：US15835399

申请日：2017-12-07

Applicant: KLA-Tencor Corporation

Inventor： Martin Plihal ,  Erfan Soltanmohammadi ,  Saravanan Paramasivam ,  Sairam Ravu ,  Ankit Jain ,  Prasanti Uppaluri ,  Vijay Ramachandran

IPC: G01N21/95 ,  H01L21/67 ,  G05B19/418 ,  G01N21/88 ,  G06T7/00 ,  H01J37/22 ,  H01J37/28 ,  G01N23/04 ,  H01L21/66 ,  G06N7/00

Abstract: Wafer inspection with stable nuisance rates and defect of interest capture rates are disclosed. This technique can be used for discovery of newly appearing defects that occur during the manufacturing process. Based on a first wafer, defects of interest are identified based on the classified filtered inspection results. For each remaining wafer, the defect classifier is updated and defects of interest in the next wafer are identified based on the classified filtered inspection results.

公开(公告)号：US10267748B2

公开(公告)日：2019-04-23

申请号：US15782820

申请日：2017-10-12

Applicant: KLA-Tencor Corporation

Inventor： Martin Plihal ,  Erfan Soltanmohammadi ,  Saravanan Paramasivam ,  Sairam Ravu ,  Ankit Jain ,  Sarath Shekkizhar ,  Prasanti Uppaluri

IPC: G06N5/00 ,  G01N21/55 ,  G01N21/88 ,  G01N21/95 ,  G06N99/00 ,  G01N21/956

Abstract: Methods and systems for training an inspection-related algorithm are provided. One system includes one or more computer subsystems configured for performing an initial training of an inspection-related algorithm with a labeled set of defects thereby generating an initial version of the inspection-related algorithm and applying the initial version of the inspection-related algorithm to an unlabeled set of defects. The computer subsystem(s) are also configured for altering the labeled set of defects based on results of the applying. The computer subsystem(s) may then iteratively re-train the inspection-related algorithm and alter the labeled set of defects until one or more differences between results produced by a most recent version and a previous version of the algorithm meet one or more criteria. When the one or more differences meet the one or more criteria, the most recent version of the inspection-related algorithm is outputted as the trained algorithm.

公开(公告)号：US20180106732A1

公开(公告)日：2018-04-19

申请号：US15782820

申请日：2017-10-12

Applicant: KLA-Tencor Corporation

Inventor： Martin Plihal ,  Erfan Soltanmohammadi ,  Saravanan Paramasivam ,  Sairam Ravu ,  Ankit Jain ,  Sarath Shekkizhar ,  Prasanti Uppaluri

IPC: G01N21/95 ,  G01N21/88 ,  G01N21/55 ,  G06N99/00

CPC classification number: G01N21/9501 ,  G01N21/55 ,  G01N21/8803 ,  G01N21/8851 ,  G01N2021/8854 ,  G01N2021/95676 ,  G06N5/003 ,  G06N99/005

Abstract: Methods and systems for training an inspection-related algorithm are provided. One system includes one or more computer subsystems configured for performing an initial training of an inspection-related algorithm with a labeled set of defects thereby generating an initial version of the inspection-related algorithm and applying the initial version of the inspection-related algorithm to an unlabeled set of defects. The computer subsystem(s) are also configured for altering the labeled set of defects based on results of the applying. The computer subsystem(s) may then iteratively re-train the inspection-related algorithm and alter the labeled set of defects until one or more differences between results produced by a most recent version and a previous version of the algorithm meet one or more criteria. When the one or more differences meet the one or more criteria, the most recent version of the inspection-related algorithm is outputted as the trained algorithm.