Fault Detection and Diagnosis Based on KPCA-LSSVM Model

Author

Li, Zhonghai ; Zhang, Yan ; Jiang, Liying

Author_Institution

Coll. of Autom., Shenyang Inst. of Aeronaut. Eng., Shenyang, China

Volume

1

fYear

2009

fDate

11-12 April 2009

Firstpage

634

Lastpage

638

Abstract

Although Kernel Principle Component Analysis(KPCA)has been used to monitoring nonlinear processes, it is not well suited for fault diagnosis. In order to solve this problem, a new method of fault detection and diagnosis for nonlinear processes based on KPCA and Least Squares Support Vector Machine(LSSVM) is proposed. The KPCA is used to monitor faults and extract feature and LSSVM model is used to diagnose fault, LSSVM model is constructed based on nonlinear principle component scores of various known faults. The applications in TE process illustrate the efficiency of the proposed approach.

Keywords

chemical technology; fault diagnosis; least squares approximations; principal component analysis; production engineering computing; support vector machines; fault detection; fault diagnosis; fault monitoring; feature extraction; kernel principle component analysis; least squares support vector machine; nonlinear processes monitoring; Automation; Fault detection; Fault diagnosis; Kernel; Least squares methods; Matrix converters; Principal component analysis; Space technology; Support vector machine classification; Support vector machines; Fault detecion; Fault diagnosis; KPCA; LSSVM;

fLanguage

English

Publisher

ieee

Conference_Titel

Measuring Technology and Mechatronics Automation, 2009. ICMTMA '09. International Conference on

Conference_Location

Zhangjiajie, Hunan

Print_ISBN

978-0-7695-3583-8

Type

conf

DOI

10.1109/ICMTMA.2009.465

Filename

5203052