Statistical comparison of fault detection models for semiconductor manufacturing processes

Taehyung Lee, Chang Ouk Kim

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

A variety of statistical and data-mining techniques have been developed for the fault detection (FD) modeling of semiconductor manufacturing processes over the past three decades. However, few studies have analyzed which models are adequate for different types of fault data. In this paper, we define a FD model as an algorithm combining feature extraction, feature selection, and classification. We prepare six process data scenarios and collect data by simulating an etching tool. In total, 117 possible algorithm combinations are tested as FD models for the six datasets. With these test results, we conduct statistical analyses from two perspectives: 1) the algorithm perspective and 2) FD model perspective. From the algorithm perspective, we compare the performance of competing algorithms in the three model-building steps using multiple comparison methods and discuss the advantages and disadvantages of individual algorithms. From the model perspective, we determine which algorithm combinations are recommended for FD models of the semiconductor process and explain why some combinations do not exhibit the expected performance. In both analyses, we interpret some results using 3-D plots.

Original languageEnglish
Article number6979239
Pages (from-to)80-91
Number of pages12
JournalIEEE Transactions on Semiconductor Manufacturing
Volume28
Issue number1
DOIs
Publication statusPublished - 2015 Feb 1

Fingerprint

fault detection
Fault detection
manufacturing
Semiconductor materials
Feature extraction
data mining
pattern recognition
Data mining
Etching
plots
etching

All Science Journal Classification (ASJC) codes

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

Cite this

@article{3903f617e8f94d9f89ab15a6869f0f5d,
title = "Statistical comparison of fault detection models for semiconductor manufacturing processes",
abstract = "A variety of statistical and data-mining techniques have been developed for the fault detection (FD) modeling of semiconductor manufacturing processes over the past three decades. However, few studies have analyzed which models are adequate for different types of fault data. In this paper, we define a FD model as an algorithm combining feature extraction, feature selection, and classification. We prepare six process data scenarios and collect data by simulating an etching tool. In total, 117 possible algorithm combinations are tested as FD models for the six datasets. With these test results, we conduct statistical analyses from two perspectives: 1) the algorithm perspective and 2) FD model perspective. From the algorithm perspective, we compare the performance of competing algorithms in the three model-building steps using multiple comparison methods and discuss the advantages and disadvantages of individual algorithms. From the model perspective, we determine which algorithm combinations are recommended for FD models of the semiconductor process and explain why some combinations do not exhibit the expected performance. In both analyses, we interpret some results using 3-D plots.",
author = "Taehyung Lee and Kim, {Chang Ouk}",
year = "2015",
month = "2",
day = "1",
doi = "10.1109/TSM.2014.2378796",
language = "English",
volume = "28",
pages = "80--91",
journal = "IEEE Transactions on Semiconductor Manufacturing",
issn = "0894-6507",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

Statistical comparison of fault detection models for semiconductor manufacturing processes. / Lee, Taehyung; Kim, Chang Ouk.

In: IEEE Transactions on Semiconductor Manufacturing, Vol. 28, No. 1, 6979239, 01.02.2015, p. 80-91.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Statistical comparison of fault detection models for semiconductor manufacturing processes

AU - Lee, Taehyung

AU - Kim, Chang Ouk

PY - 2015/2/1

Y1 - 2015/2/1

N2 - A variety of statistical and data-mining techniques have been developed for the fault detection (FD) modeling of semiconductor manufacturing processes over the past three decades. However, few studies have analyzed which models are adequate for different types of fault data. In this paper, we define a FD model as an algorithm combining feature extraction, feature selection, and classification. We prepare six process data scenarios and collect data by simulating an etching tool. In total, 117 possible algorithm combinations are tested as FD models for the six datasets. With these test results, we conduct statistical analyses from two perspectives: 1) the algorithm perspective and 2) FD model perspective. From the algorithm perspective, we compare the performance of competing algorithms in the three model-building steps using multiple comparison methods and discuss the advantages and disadvantages of individual algorithms. From the model perspective, we determine which algorithm combinations are recommended for FD models of the semiconductor process and explain why some combinations do not exhibit the expected performance. In both analyses, we interpret some results using 3-D plots.

AB - A variety of statistical and data-mining techniques have been developed for the fault detection (FD) modeling of semiconductor manufacturing processes over the past three decades. However, few studies have analyzed which models are adequate for different types of fault data. In this paper, we define a FD model as an algorithm combining feature extraction, feature selection, and classification. We prepare six process data scenarios and collect data by simulating an etching tool. In total, 117 possible algorithm combinations are tested as FD models for the six datasets. With these test results, we conduct statistical analyses from two perspectives: 1) the algorithm perspective and 2) FD model perspective. From the algorithm perspective, we compare the performance of competing algorithms in the three model-building steps using multiple comparison methods and discuss the advantages and disadvantages of individual algorithms. From the model perspective, we determine which algorithm combinations are recommended for FD models of the semiconductor process and explain why some combinations do not exhibit the expected performance. In both analyses, we interpret some results using 3-D plots.

UR - http://www.scopus.com/inward/record.url?scp=84922588455&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922588455&partnerID=8YFLogxK

U2 - 10.1109/TSM.2014.2378796

DO - 10.1109/TSM.2014.2378796

M3 - Article

AN - SCOPUS:84922588455

VL - 28

SP - 80

EP - 91

JO - IEEE Transactions on Semiconductor Manufacturing

JF - IEEE Transactions on Semiconductor Manufacturing

SN - 0894-6507

IS - 1

M1 - 6979239

ER -