Combining KPCA and LSSVM for HVAC Fan Machinery Fault Recognition
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.
Li Xuemei Ding Lixing Li Jincheng Xu Gang
School of Mechanical and Automotive Engineering,South China University of Technology,Guangzhou Schoo Institute of Built Environment and Control,Zhongkai University of Agriculture and Engineering,Guangz School of Mechanical and Electrical Engineering,Zhongkai University of Agriculture and Engineering,G School of Mechatronics and Control Engineering,Shenzhen University,Shenzhen,China,518060
国际会议
2009 IEEE International Conference on Robotics and Biomimetics(2009 IEEE 机器人与仿生技术国际会议 ROBIO 2009)
桂林
英文
1241-1246
2009-12-19（万方平台首次上网日期，不代表论文的发表时间）