Support Vector Machine-Regression을 이용한 주기신호의 이상탐지 = A Fault Detection of Cyclic Signals Using Support Vector Machine-Regression

다국어 초록 (Multilingual Abstract)

This paper presents a non-linear control chart based on support vector machine regression (SVM-R) to improve the accuracy of fault detection of cyclic signals. The proposed algorithm consists of the following two steps. First, the center line of the control chart is constructed by using SVM-R. Second, we calculate control limits by variances that are estimated by perpendicular and normal line of the center line. For performance evaluation, we apply proposed algorithm to the industrial data of the chemical vapor deposition process which is one of the semiconductor processes. The proposed method has better fault detection performance than other existing method

참고문헌 (Reference)

1 "http://www.public.itrs.ne"

2 Vapnik,V, "The Statistical Learning Theory" John Wiley & Sons, Inc. 1998

3 Vapnik,V, "The Nature of Statistical Learning Therory" Springer-Verlag 1995

4 박찬규, "Support Vector Regression을 이용한 소프트웨어 개발비 예측" 한국경영과학회 23 (23): 75-92, 2006

5 Montgomery,D.C, "Introduction to Statistical Quality Control" Hohn Wiley & Sons 2001

6 Shi,J, "Diagnostic feature extraction from stamping tonnage signals based on design of experiments" 122 (122): 360-369, 2000

7 Nello,C, "An Introduction to Support Vector Machine"

8 Smola,A, "A tutorial on support vector regression" 14 : 199-222, 2004

9 Burges,C.J.C, "A tutorial on support vector machines for pattern recongnition" 2 (2): 121-167, 1998