A deep learning model for robust wafer fault monitoring with sensor measurement noise

Hoyeop Lee, Youngju Kim, Chang Ouk Kim

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Standard fault detection and classification (FDC) models detect wafer faults by extracting features useful for fault detection from time-indexed measurements of the equipment recorded by in situ sensors (sensor signals) and feeding the extracted information into a classifier. However, the preprocessing-and-classification approach often results in the loss of information in the sensor signals that is important for detecting wafer faults. Furthermore, the sensor signals usually contain noise induced by mechanical and electrical disturbances. In this paper, we propose the use of a stacked denoising autoencoder (SdA), which is a deep learning algorithm, to establish an FDC model for simultaneous feature extraction and classification. The SdA model can identify global and invariant features in the sensor signals for fault monitoring and is robust against measurement noise. Through experiments using wafer samples collected from a work-site photolithography tool, we confirmed that as the sensor measurement noise severity increased, the SdA's classification accuracy could be as much as 14% higher than those of the twelve models considered for comparison, each of which employed one of three feature extractors and one of four classifiers.

Original languageEnglish
Article number7744687
Pages (from-to)23-31
Number of pages9
JournalIEEE Transactions on Semiconductor Manufacturing
Volume30
Issue number1
DOIs
Publication statusPublished - 2017 Feb 1

Fingerprint

noise measurement
learning
wafers
fault detection
Monitoring
sensors
Sensors
Fault detection
classifiers
Classifiers
Photolithography
preprocessing
photolithography
Time measurement
pattern recognition
Learning algorithms
Deep learning
Feature extraction
disturbances
time measurement

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Cite this

@article{b913c211f9744a8587e99c89ecf787a6,
title = "A deep learning model for robust wafer fault monitoring with sensor measurement noise",
abstract = "Standard fault detection and classification (FDC) models detect wafer faults by extracting features useful for fault detection from time-indexed measurements of the equipment recorded by in situ sensors (sensor signals) and feeding the extracted information into a classifier. However, the preprocessing-and-classification approach often results in the loss of information in the sensor signals that is important for detecting wafer faults. Furthermore, the sensor signals usually contain noise induced by mechanical and electrical disturbances. In this paper, we propose the use of a stacked denoising autoencoder (SdA), which is a deep learning algorithm, to establish an FDC model for simultaneous feature extraction and classification. The SdA model can identify global and invariant features in the sensor signals for fault monitoring and is robust against measurement noise. Through experiments using wafer samples collected from a work-site photolithography tool, we confirmed that as the sensor measurement noise severity increased, the SdA's classification accuracy could be as much as 14{\%} higher than those of the twelve models considered for comparison, each of which employed one of three feature extractors and one of four classifiers.",
author = "Hoyeop Lee and Youngju Kim and Kim, {Chang Ouk}",
year = "2017",
month = "2",
day = "1",
doi = "10.1109/TSM.2016.2628865",
language = "English",
volume = "30",
pages = "23--31",
journal = "IEEE Transactions on Semiconductor Manufacturing",
issn = "0894-6507",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

A deep learning model for robust wafer fault monitoring with sensor measurement noise. / Lee, Hoyeop; Kim, Youngju; Kim, Chang Ouk.

In: IEEE Transactions on Semiconductor Manufacturing, Vol. 30, No. 1, 7744687, 01.02.2017, p. 23-31.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A deep learning model for robust wafer fault monitoring with sensor measurement noise

AU - Lee, Hoyeop

AU - Kim, Youngju

AU - Kim, Chang Ouk

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Standard fault detection and classification (FDC) models detect wafer faults by extracting features useful for fault detection from time-indexed measurements of the equipment recorded by in situ sensors (sensor signals) and feeding the extracted information into a classifier. However, the preprocessing-and-classification approach often results in the loss of information in the sensor signals that is important for detecting wafer faults. Furthermore, the sensor signals usually contain noise induced by mechanical and electrical disturbances. In this paper, we propose the use of a stacked denoising autoencoder (SdA), which is a deep learning algorithm, to establish an FDC model for simultaneous feature extraction and classification. The SdA model can identify global and invariant features in the sensor signals for fault monitoring and is robust against measurement noise. Through experiments using wafer samples collected from a work-site photolithography tool, we confirmed that as the sensor measurement noise severity increased, the SdA's classification accuracy could be as much as 14% higher than those of the twelve models considered for comparison, each of which employed one of three feature extractors and one of four classifiers.

AB - Standard fault detection and classification (FDC) models detect wafer faults by extracting features useful for fault detection from time-indexed measurements of the equipment recorded by in situ sensors (sensor signals) and feeding the extracted information into a classifier. However, the preprocessing-and-classification approach often results in the loss of information in the sensor signals that is important for detecting wafer faults. Furthermore, the sensor signals usually contain noise induced by mechanical and electrical disturbances. In this paper, we propose the use of a stacked denoising autoencoder (SdA), which is a deep learning algorithm, to establish an FDC model for simultaneous feature extraction and classification. The SdA model can identify global and invariant features in the sensor signals for fault monitoring and is robust against measurement noise. Through experiments using wafer samples collected from a work-site photolithography tool, we confirmed that as the sensor measurement noise severity increased, the SdA's classification accuracy could be as much as 14% higher than those of the twelve models considered for comparison, each of which employed one of three feature extractors and one of four classifiers.

UR - http://www.scopus.com/inward/record.url?scp=85012863132&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012863132&partnerID=8YFLogxK

U2 - 10.1109/TSM.2016.2628865

DO - 10.1109/TSM.2016.2628865

M3 - Article

VL - 30

SP - 23

EP - 31

JO - IEEE Transactions on Semiconductor Manufacturing

JF - IEEE Transactions on Semiconductor Manufacturing

SN - 0894-6507

IS - 1

M1 - 7744687

ER -