Fault Diagnosis Research of TWERD Frequency Converter Based on Wavelet Transform
作者单位：Wenhua Xi Road 2 Harbin Institute of Technology at Weihai Haibin Bei Road 48 Weihai Weidong Ferry Co.LTD
会议名称：《The International Conference on Recent Trends in Materials and Mechanical Engineering(ICRTMME 2011)》
会议日期：1000年
学科分类：080804[工学-电力电子与电力传动] 0808[工学-电气工程] 08[工学]
关 键 词：Frequency converter Wavelet transform BP neural network Fault diagnosis
摘 要：Taking TWERD frequency converter as research object, the working principle and fault types of three-phase SPWM inverter are analyzedIts output line voltage waveform in normal operation and fault condition is studiedAccording to the fault information and the different data of input and load changes, the frequency converter output line voltage waveform is decomposed by wavelet transformThe low frequency energy value is picked-up and regards it as eigenvectorThe mapping relationship between eigenvector and fault types are established by BP neural network, the fault bridge and fault location of frequency converter are foundSimulation results show that the diagnosis accuracy is 96.5% after training 46 timesFast convergence speed and high precision is obtained.