Combining KPCA and LSSVM for HVAC fan machinery fault recognition

Authors:
Li Xuemei;Ding Lixing;Li Jincheng;Xu Gang
Affiliations:
School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, China and School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and ...;Institute of Built Environment and Control, Zhongkai University of Agriculture and Engineering, Guangzhou, China;School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou, China;School of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, China
Venue:
ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
Year:
2009

Citing 3
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Nonlinear component analysis as a kernel eigenvalue problem

Neural Computation
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a novel approach combining kernel principal component analysis (KPCA) and least square support vector machine (LSSVM) is proposed for HVAC fan machinery status monitoring and fault diagnosis, which combines KPCA for fault feature extraction and multiple SVMs (MSVMs) for identification of different fault sources. KPCA is used as a preprocessor of LSSVM, which maps the original input feature into a higher dimension feature space through a nonlinear map, the principal components are then found in the higher dimension feature space. Then the hyperparameters of LSSVM are optimized by particle swarm optimization. Then we compared the accuracies of the hybrid KPCA-LSSVM mode with other artificial intelligence (BPNN and fixed-SVM). The experimental results showed that KPCA based on LS-SVM has a higher correct recognition rate, and a faster computational speed.