Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing

Simon Zabrocki; Pil Sung Jo; Chan Park; Dongkyun Yim; Sunghee Yun; Byung Jun Lee

doi:10.1109/ASMC57536.2023.10121099

Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing

Simon Zabrocki, Pil Sung Jo, Chan Park, Dongkyun Yim, Sunghee Yun, Byung Jun Lee

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

2 Citations (Scopus)

Abstract

This paper proposes a novel highly accurate virtual metrology (VM) method based on adaptive online time-series learning. The method comprises a novel time-series prediction algorithm robust against data drifts and shifts observed in semi-conductor manufacturing. The prediction algorithm incorporates time-aware data normalization and adaptive online learning. The time-aware normalizer transforms the data to suppress the effect of drifts. The adaptive online learner captures the time-varying relationship between response and inputs caused by shifts. On both simulated and real process data our approach outperforms conventional VM approaches. When applied to advanced process control (APC) on high-volume production lines at a major semiconductor manufacturer, our VM method substantially reduced variability of process outcomes.

Original language	English
Title of host publication	2023 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665456395
DOIs	https://doi.org/10.1109/ASMC57536.2023.10121099
Publication status	Published - 2023
Event	34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023 - Saratoga Springs, United States Duration: 2023 May 1 → 2023 May 4

Publication series

Name	ASMC (Advanced Semiconductor Manufacturing Conference) Proceedings
Volume	2023-May
ISSN (Print)	1078-8743

Conference

Conference	34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023
Country/Territory	United States
City	Saratoga Springs
Period	23/5/1 → 23/5/4

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

adaptive learning algorithm
advanced process control (APC)
data drifts and shifts
time-series prediction
virtual metrology (VM)

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
General Engineering
Industrial and Manufacturing Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/ASMC57536.2023.10121099

Cite this

Zabrocki, S., Jo, P. S., Park, C., Yim, D., Yun, S., & Lee, B. J. (2023). Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing. In 2023 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023 (ASMC (Advanced Semiconductor Manufacturing Conference) Proceedings; Vol. 2023-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASMC57536.2023.10121099

Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing. / Zabrocki, Simon; Jo, Pil Sung; Park, Chan et al.
2023 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (ASMC (Advanced Semiconductor Manufacturing Conference) Proceedings; Vol. 2023-May).

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

Zabrocki, S, Jo, PS, Park, C, Yim, D, Yun, S & Lee, BJ 2023, Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing. in 2023 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023. ASMC (Advanced Semiconductor Manufacturing Conference) Proceedings, vol. 2023-May, Institute of Electrical and Electronics Engineers Inc., 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023, Saratoga Springs, United States, 23/5/1. https://doi.org/10.1109/ASMC57536.2023.10121099

Zabrocki S, Jo PS, Park C, Yim D, Yun S, Lee BJ. Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing. In 2023 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (ASMC (Advanced Semiconductor Manufacturing Conference) Proceedings). doi: 10.1109/ASMC57536.2023.10121099

@inproceedings{2dc794c5a7b247e1ba7b617744490235,

title = "Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing",

abstract = "This paper proposes a novel highly accurate virtual metrology (VM) method based on adaptive online time-series learning. The method comprises a novel time-series prediction algorithm robust against data drifts and shifts observed in semi-conductor manufacturing. The prediction algorithm incorporates time-aware data normalization and adaptive online learning. The time-aware normalizer transforms the data to suppress the effect of drifts. The adaptive online learner captures the time-varying relationship between response and inputs caused by shifts. On both simulated and real process data our approach outperforms conventional VM approaches. When applied to advanced process control (APC) on high-volume production lines at a major semiconductor manufacturer, our VM method substantially reduced variability of process outcomes.",

keywords = "adaptive learning algorithm, advanced process control (APC), data drifts and shifts, time-series prediction, virtual metrology (VM)",

author = "Simon Zabrocki and Jo, {Pil Sung} and Chan Park and Dongkyun Yim and Sunghee Yun and Lee, {Byung Jun}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023 ; Conference date: 01-05-2023 Through 04-05-2023",

year = "2023",

doi = "10.1109/ASMC57536.2023.10121099",

language = "English",

series = "ASMC (Advanced Semiconductor Manufacturing Conference) Proceedings",

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

booktitle = "2023 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023",

}

TY - GEN

T1 - Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing

AU - Zabrocki, Simon

AU - Jo, Pil Sung

AU - Park, Chan

AU - Yim, Dongkyun

AU - Yun, Sunghee

AU - Lee, Byung Jun

PY - 2023

Y1 - 2023

N2 - This paper proposes a novel highly accurate virtual metrology (VM) method based on adaptive online time-series learning. The method comprises a novel time-series prediction algorithm robust against data drifts and shifts observed in semi-conductor manufacturing. The prediction algorithm incorporates time-aware data normalization and adaptive online learning. The time-aware normalizer transforms the data to suppress the effect of drifts. The adaptive online learner captures the time-varying relationship between response and inputs caused by shifts. On both simulated and real process data our approach outperforms conventional VM approaches. When applied to advanced process control (APC) on high-volume production lines at a major semiconductor manufacturer, our VM method substantially reduced variability of process outcomes.

AB - This paper proposes a novel highly accurate virtual metrology (VM) method based on adaptive online time-series learning. The method comprises a novel time-series prediction algorithm robust against data drifts and shifts observed in semi-conductor manufacturing. The prediction algorithm incorporates time-aware data normalization and adaptive online learning. The time-aware normalizer transforms the data to suppress the effect of drifts. The adaptive online learner captures the time-varying relationship between response and inputs caused by shifts. On both simulated and real process data our approach outperforms conventional VM approaches. When applied to advanced process control (APC) on high-volume production lines at a major semiconductor manufacturer, our VM method substantially reduced variability of process outcomes.

KW - adaptive learning algorithm

KW - advanced process control (APC)

KW - data drifts and shifts

KW - time-series prediction

KW - virtual metrology (VM)

UR - http://www.scopus.com/inward/record.url?scp=85159766712&partnerID=8YFLogxK

U2 - 10.1109/ASMC57536.2023.10121099

DO - 10.1109/ASMC57536.2023.10121099

M3 - Conference contribution

AN - SCOPUS:85159766712

T3 - ASMC (Advanced Semiconductor Manufacturing Conference) Proceedings

BT - 2023 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 34th Annual SEMI Advanced Semiconductor Manufacturing Conference, ASMC 2023

Y2 - 1 May 2023 through 4 May 2023

ER -

Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this