Application of Affinity Propagation Clustering Algorithm in Fault Diagnosis of Metro Vehicle Auxiliary Inverter
Auxiliary inverter is one of the most important electrical equipments of metro vehicle; its complex structure causes various faults frequently. In this paper, the fundamental of the Affinity Propagation algorithm is introduced, and its application on fault diagnosis of metro vehicle auxiliary inverter is studied. Fault signals including voltage frequency variation, pulse transient, and power interruption are simulated by using the MATLAB software; clustering center matrix is calculated on the basis of AP algorithm, and the fault samples are classified by calculating the similarity degree between samples and clustering center. The simulation results show that the AP algorithm without initial clustering center can be used in the field of fault diagnosis, and even has better results than FCM algorithm.
KeywordsAffinity propagation Fault diagnosis Auxiliary inverter Clustering analysis
This work is partially supported by the National Science and Technology Pillar Program (2011BAG01B05), the Foundation of Shandong Province (BS2011DX008,ZR2011FM008), and the State Key Laboratory of Rail Traffic Control and Safety Foundation (RCS2011K005), Beijing Jiaotong University.
- 1.Yao DC, Yang JW, Yin YF et al (2010) Fault diagnosis of railway bearing based on muti-method fusion techniques. Mach Des Res 26(3):70–73 (in Chinese)Google Scholar
- 4.Ma ZT, Gao JW, Leng ZW et al (2013) A method of metro vehicle auxiliary inverter fault diagnosis based on fuzzy clustering arithmetic. J Qingdao Univ Eng Technol Ed 28(3):8–14 (in Chinese)Google Scholar
- 6.Gao JW, Yu JP, Leng ZW et al (2013) The application of PSO-LSSVM in fault diagnosis of subway auxiliary inverter. ICIC Express Lett 4(3):777–784Google Scholar
- 8.Xiong H, Sun CX, Liao RJ et al (2005) Study on kernel-based possibilistic clustering and dissolved gas analysis for fault diagnosis of power transformer. Proc CSEE 25(20):163–167 (in Chinese)Google Scholar