Improved Kernel Principal Component Analysis and Its Application for Fault Detection

Authors:
Chuyao Chen;Daqi Zhu;Qian Liu
Affiliations:
Information Engineering College, Shanghai Maritime University, Shanghai, China 200135;Information Engineering College, Shanghai Maritime University, Shanghai, China 200135;Information Engineering College, Shanghai Maritime University, Shanghai, China 200135
Venue:
ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Theoretical and Methodological Issues
Year:
2008

Citing 1
Cited 0

Improved kernel principal component analysis for fault detection

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

The kernel principal component analysis (KPCA) based on feature vector selection (FVS) is proposed in this paper for fault detection in nonlinear system. Firstly, the KPCA algorithm is described in detail. Secondly, a feature vector selection (FVS) scheme based on a geometric consideration is adopted to reduce the computational cost of KPCA. Finally, the KPCA and KPCA based on FVS (FVS-KPCA) are applied to a simple nonlinear system. The fault detection results and the comparison confirm the superiority of FVS-KPCA in fault detection.