Fault diagnosis method for power electronic based on wavelet transform and extreme learning machine

摘要：

　　In this paper,a novel method is presented to detect and diagnosis faults in the inverter.In this method,the features are extracted from the phase currents by the wavelet transform,and the extreme learning machine(ELM)are used to locate the fault device.The ELM has faster learning speed,and this diagnosis method has higher location rates.Experiment for the three-phase full-bridge inverter demonstrates that the proposed method is feasible and valid for the fault diagnosis of the inverters.

关键词： Fault diagnosis inverter wavelet Transform

作者: Chen Li Cai Hongjun Tang Shengxue Wang Jingqin

作者单位: Province-Ministry Joint Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability,Hebei University of Technology,Tianjin 300130,China

会议类型: 国际会议

会议名称: The Fifth International Symposium on Test Automation & Instrumentation(2014第五届国际测试自动化与仪器仪表学术会议)

会议地点: 北京

会议语种:英文

页码: 27-31

在线出版日期: 2014-09-23（万方平台首次上网日期，不代表论文的发表时间）