A Fault Detection of Cyclic Signals Using Support Vector Machine-Regression

Park, Seung-Hwan; Kim, Jun-Seok; Park, Cheong-Sool; Kim, Sung-Shick; Baek, Jun-Geol

Journal of Korean Society for Quality Management > Volume 38(3); 2010 > Article

Journal of Korean Society for Quality Management 2010;38(3): 354-.

Support Vector Machine-Regression을 이용한 주기신호의 이상탐지

박승환, 김준석, 박정술, 김성식, 백준걸

고려대학교 산업경영공학과

A Fault Detection of Cyclic Signals Using Support Vector Machine-Regression

Seung-Hwan Park, Jun-Seok Kim, Cheong-Sool Park, Sung-Shick Kim, Jun-Geol Baek

Department of Industrial Management Engineering, Korea University

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

Key Words: Fault Detection;Cyclic Signals;Support Vector Machine-Regression;