Spline regression based feature extraction for semiconductor process fault detection using support vector machine

Jonghyuck Park, Ick Hyun Kwon, Sung Shick Kim, Jun-Geol Baek

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Quality control is attracting more attention in semiconductor market due to harsh competition. This paper considers Fault Detection (FD), a well-known philosophy in quality control. Conventional methods, such as non-stationary SPC chart, PCA, PLS, and Hotelling's T2, are widely used to detect faults. However, even for identical processes, the process time differs. Missing data may hinder fault detection. Artificial intelligence (AI) techniques are used to deal with these problems. In this paper, a new fault detection method using spline regression and Support Vector Machine (SVM) is proposed. For a given process signal, spline regression is applied regarding step changing points as knot points. The coefficients multiplied to the basis of the spline function are considered as the features for the signal. SVM uses those extracted features as input variables to construct the classifier for fault detection. Numerical experiments are conducted in the case of artificial data that replicates semiconductor manufacturing signals to evaluate the performance of the proposed method.

Original languageEnglish
Pages (from-to)5711-5718
Number of pages8
JournalExpert Systems with Applications
Volume38
Issue number5
DOIs
Publication statusPublished - 2011 May 1

Fingerprint

Fault detection
Splines
Support vector machines
Feature extraction
Semiconductor materials
Quality control
Artificial intelligence
Classifiers
Experiments

Keywords

  • Fault detection
  • Feature extraction
  • Semiconductor manufacturing
  • Spline regression
  • Support vector machine

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Engineering(all)

Cite this

Spline regression based feature extraction for semiconductor process fault detection using support vector machine. / Park, Jonghyuck; Kwon, Ick Hyun; Kim, Sung Shick; Baek, Jun-Geol.

In: Expert Systems with Applications, Vol. 38, No. 5, 01.05.2011, p. 5711-5718.

Research output: Contribution to journalArticle

@article{81ae7fb8bb7e48dab68cfb40091db9a5,
title = "Spline regression based feature extraction for semiconductor process fault detection using support vector machine",
abstract = "Quality control is attracting more attention in semiconductor market due to harsh competition. This paper considers Fault Detection (FD), a well-known philosophy in quality control. Conventional methods, such as non-stationary SPC chart, PCA, PLS, and Hotelling's T2, are widely used to detect faults. However, even for identical processes, the process time differs. Missing data may hinder fault detection. Artificial intelligence (AI) techniques are used to deal with these problems. In this paper, a new fault detection method using spline regression and Support Vector Machine (SVM) is proposed. For a given process signal, spline regression is applied regarding step changing points as knot points. The coefficients multiplied to the basis of the spline function are considered as the features for the signal. SVM uses those extracted features as input variables to construct the classifier for fault detection. Numerical experiments are conducted in the case of artificial data that replicates semiconductor manufacturing signals to evaluate the performance of the proposed method.",
keywords = "Fault detection, Feature extraction, Semiconductor manufacturing, Spline regression, Support vector machine",
author = "Jonghyuck Park and Kwon, {Ick Hyun} and Kim, {Sung Shick} and Jun-Geol Baek",
year = "2011",
month = "5",
day = "1",
doi = "10.1016/j.eswa.2010.10.062",
language = "English",
volume = "38",
pages = "5711--5718",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Spline regression based feature extraction for semiconductor process fault detection using support vector machine

AU - Park, Jonghyuck

AU - Kwon, Ick Hyun

AU - Kim, Sung Shick

AU - Baek, Jun-Geol

PY - 2011/5/1

Y1 - 2011/5/1

N2 - Quality control is attracting more attention in semiconductor market due to harsh competition. This paper considers Fault Detection (FD), a well-known philosophy in quality control. Conventional methods, such as non-stationary SPC chart, PCA, PLS, and Hotelling's T2, are widely used to detect faults. However, even for identical processes, the process time differs. Missing data may hinder fault detection. Artificial intelligence (AI) techniques are used to deal with these problems. In this paper, a new fault detection method using spline regression and Support Vector Machine (SVM) is proposed. For a given process signal, spline regression is applied regarding step changing points as knot points. The coefficients multiplied to the basis of the spline function are considered as the features for the signal. SVM uses those extracted features as input variables to construct the classifier for fault detection. Numerical experiments are conducted in the case of artificial data that replicates semiconductor manufacturing signals to evaluate the performance of the proposed method.

AB - Quality control is attracting more attention in semiconductor market due to harsh competition. This paper considers Fault Detection (FD), a well-known philosophy in quality control. Conventional methods, such as non-stationary SPC chart, PCA, PLS, and Hotelling's T2, are widely used to detect faults. However, even for identical processes, the process time differs. Missing data may hinder fault detection. Artificial intelligence (AI) techniques are used to deal with these problems. In this paper, a new fault detection method using spline regression and Support Vector Machine (SVM) is proposed. For a given process signal, spline regression is applied regarding step changing points as knot points. The coefficients multiplied to the basis of the spline function are considered as the features for the signal. SVM uses those extracted features as input variables to construct the classifier for fault detection. Numerical experiments are conducted in the case of artificial data that replicates semiconductor manufacturing signals to evaluate the performance of the proposed method.

KW - Fault detection

KW - Feature extraction

KW - Semiconductor manufacturing

KW - Spline regression

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=79151477537&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79151477537&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2010.10.062

DO - 10.1016/j.eswa.2010.10.062

M3 - Article

AN - SCOPUS:79151477537

VL - 38

SP - 5711

EP - 5718

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 5

ER -