Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology

Heung Kook Ko; Sena Park; Jihyun Ryu; Sung Ryul Kim; Giwon Lee; Dongjoon Lee; Sangwoo Pae; Euncheol Lee; Yongsun Ji; Hia Jiang; Tae Young Jeong; Taiki Uemura; Dongkyun Kwon; Hyungrok Do; Hyungu Kahng; Yoon Sang Cho; Jiyoon Lee; Seoung Bum Kim

doi:10.1109/IRPS45951.2020.9128932

Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology

Heung Kook Ko, Sena Park, Jihyun Ryu, Sung Ryul Kim, Giwon Lee, Dongjoon Lee, Sangwoo Pae, Euncheol Lee, Yongsun Ji, Hia Jiang, Tae Young Jeong, Taiki Uemura, Dongkyun Kwon, Hyungrok Do, Hyungu Kahng, Yoon Sang Cho, Jiyoon Lee, Seoung Bum Kim

School of Industrial Management Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper proposes to use machine learning (ML) methods to predict wafer quality using Fab inline measured items, DC measurements, and DVS (Dynamic Voltage Stress) at wafer sort. With developed ML approach, the predicted accuracy is more than 80% in 8 nm products used in this study. We believe this method can be further fine-tuned to help enable ICs at the high level expected for automotive systems. By assigning predictive rankings, the method also helps enable best tooling system for higher quality.

Original language	English
Title of host publication	2020 IEEE International Reliability Physics Symposium, IRPS 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728131993
DOIs	https://doi.org/10.1109/IRPS45951.2020.9128932
Publication status	Published - 2020 Apr
Event	2020 IEEE International Reliability Physics Symposium, IRPS 2020 - Virtual, Online, United States Duration: 2020 Apr 28 → 2020 May 30

Publication series

Name	IEEE International Reliability Physics Symposium Proceedings
Volume	2020-April
ISSN (Print)	1541-7026

Conference

Conference	2020 IEEE International Reliability Physics Symposium, IRPS 2020
Country	United States
City	Virtual, Online
Period	20/4/28 → 20/5/30

Keywords

Gradient Boosting
Machine Learning
Mice
Risk Prediction

ASJC Scopus subject areas

Engineering(all)

Access to Document

10.1109/IRPS45951.2020.9128932

Fingerprint Dive into the research topics of 'Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology'. Together they form a unique fingerprint.

Cite this

Ko, H. K., Park, S., Ryu, J., Kim, S. R., Lee, G., Lee, D., Pae, S., Lee, E., Ji, Y., Jiang, H., Jeong, T. Y., Uemura, T., Kwon, D., Do, H., Kahng, H., Cho, Y. S., Lee, J., & Kim, S. B. (2020). Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology. In 2020 IEEE International Reliability Physics Symposium, IRPS 2020 - Proceedings [9128932] (IEEE International Reliability Physics Symposium Proceedings; Vol. 2020-April). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IRPS45951.2020.9128932

Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology. / Ko, Heung Kook; Park, Sena; Ryu, Jihyun; Kim, Sung Ryul; Lee, Giwon; Lee, Dongjoon; Pae, Sangwoo; Lee, Euncheol; Ji, Yongsun; Jiang, Hia; Jeong, Tae Young; Uemura, Taiki; Kwon, Dongkyun; Do, Hyungrok; Kahng, Hyungu; Cho, Yoon Sang; Lee, Jiyoon; Kim, Seoung Bum.

2020 IEEE International Reliability Physics Symposium, IRPS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9128932 (IEEE International Reliability Physics Symposium Proceedings; Vol. 2020-April).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ko, HK, Park, S, Ryu, J, Kim, SR, Lee, G, Lee, D, Pae, S, Lee, E, Ji, Y, Jiang, H, Jeong, TY, Uemura, T, Kwon, D, Do, H, Kahng, H, Cho, YS, Lee, J & Kim, SB 2020, Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology. in 2020 IEEE International Reliability Physics Symposium, IRPS 2020 - Proceedings., 9128932, IEEE International Reliability Physics Symposium Proceedings, vol. 2020-April, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE International Reliability Physics Symposium, IRPS 2020, Virtual, Online, United States, 20/4/28. https://doi.org/10.1109/IRPS45951.2020.9128932

Ko HK, Park S, Ryu J, Kim SR, Lee G, Lee D et al. Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology. In 2020 IEEE International Reliability Physics Symposium, IRPS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9128932. (IEEE International Reliability Physics Symposium Proceedings). https://doi.org/10.1109/IRPS45951.2020.9128932

Ko, Heung Kook ; Park, Sena ; Ryu, Jihyun ; Kim, Sung Ryul ; Lee, Giwon ; Lee, Dongjoon ; Pae, Sangwoo ; Lee, Euncheol ; Ji, Yongsun ; Jiang, Hia ; Jeong, Tae Young ; Uemura, Taiki ; Kwon, Dongkyun ; Do, Hyungrok ; Kahng, Hyungu ; Cho, Yoon Sang ; Lee, Jiyoon ; Kim, Seoung Bum. / Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology. 2020 IEEE International Reliability Physics Symposium, IRPS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (IEEE International Reliability Physics Symposium Proceedings).

@inproceedings{eaa05a3bc2204e68b98c358c2d82673d,

title = "Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology",

abstract = "This paper proposes to use machine learning (ML) methods to predict wafer quality using Fab inline measured items, DC measurements, and DVS (Dynamic Voltage Stress) at wafer sort. With developed ML approach, the predicted accuracy is more than 80% in 8 nm products used in this study. We believe this method can be further fine-tuned to help enable ICs at the high level expected for automotive systems. By assigning predictive rankings, the method also helps enable best tooling system for higher quality.",

keywords = "Gradient Boosting, Machine Learning, Mice, Risk Prediction",

author = "Ko, {Heung Kook} and Sena Park and Jihyun Ryu and Kim, {Sung Ryul} and Giwon Lee and Dongjoon Lee and Sangwoo Pae and Euncheol Lee and Yongsun Ji and Hia Jiang and Jeong, {Tae Young} and Taiki Uemura and Dongkyun Kwon and Hyungrok Do and Hyungu Kahng and Cho, {Yoon Sang} and Jiyoon Lee and Kim, {Seoung Bum}",

year = "2020",

month = apr,

doi = "10.1109/IRPS45951.2020.9128932",

language = "English",

series = "IEEE International Reliability Physics Symposium Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 IEEE International Reliability Physics Symposium, IRPS 2020 - Proceedings",

note = "2020 IEEE International Reliability Physics Symposium, IRPS 2020 ; Conference date: 28-04-2020 Through 30-05-2020",

}

TY - GEN

T1 - Early Diagnosis and Prediction of Wafer Quality Using Machine Learning on sub-10nm Logic Technology

AU - Ko, Heung Kook

AU - Park, Sena

AU - Ryu, Jihyun

AU - Kim, Sung Ryul

AU - Lee, Giwon

AU - Lee, Dongjoon

AU - Pae, Sangwoo

AU - Lee, Euncheol

AU - Ji, Yongsun

AU - Jiang, Hia

AU - Jeong, Tae Young

AU - Uemura, Taiki

AU - Kwon, Dongkyun

AU - Do, Hyungrok

AU - Kahng, Hyungu

AU - Cho, Yoon Sang

AU - Lee, Jiyoon

AU - Kim, Seoung Bum

PY - 2020/4

Y1 - 2020/4

N2 - This paper proposes to use machine learning (ML) methods to predict wafer quality using Fab inline measured items, DC measurements, and DVS (Dynamic Voltage Stress) at wafer sort. With developed ML approach, the predicted accuracy is more than 80% in 8 nm products used in this study. We believe this method can be further fine-tuned to help enable ICs at the high level expected for automotive systems. By assigning predictive rankings, the method also helps enable best tooling system for higher quality.

AB - This paper proposes to use machine learning (ML) methods to predict wafer quality using Fab inline measured items, DC measurements, and DVS (Dynamic Voltage Stress) at wafer sort. With developed ML approach, the predicted accuracy is more than 80% in 8 nm products used in this study. We believe this method can be further fine-tuned to help enable ICs at the high level expected for automotive systems. By assigning predictive rankings, the method also helps enable best tooling system for higher quality.

KW - Gradient Boosting

KW - Machine Learning

KW - Mice

KW - Risk Prediction

UR - http://www.scopus.com/inward/record.url?scp=85088363971&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85088363971&partnerID=8YFLogxK

U2 - 10.1109/IRPS45951.2020.9128932

DO - 10.1109/IRPS45951.2020.9128932

M3 - Conference contribution

AN - SCOPUS:85088363971

T3 - IEEE International Reliability Physics Symposium Proceedings

BT - 2020 IEEE International Reliability Physics Symposium, IRPS 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Reliability Physics Symposium, IRPS 2020

Y2 - 28 April 2020 through 30 May 2020

ER -