电测与仪表2016，Vol.53Issue(14)：34-38,45,6.
基于极值比值法和神经网络的逆变器故障诊断
Fault diagnosis for inverter based on extremum value ratio and probabilistic neural network
摘要
Abstract
According to the open-circuit fault of each phase current characteristics ,taking fault current as the fault in-formation,this paper proposes a switch open-circuit fault diagnosis method based on extremum value ratio of three-phase current and probabilistic neural network for the three-phase PWM inverter .This method takes the extremum val-ue ratio of each phase output current as the fault characteristic ,using the nonlinear mapping classification ability of the probabilistic neural network to realize the fault diagnosis of inverter .The simulation results show that this method can accurately detect and locate failure power switch and has good robustness for noise .关键词
逆变器/开路故障诊断/极值比值/神经网络Key words
inverter/switch open-circuit fault diagnosis/extremum value ratio/neural network分类
信息技术与安全科学引用本文复制引用
袁国森,张彼德,李明昆,姚伟..基于极值比值法和神经网络的逆变器故障诊断[J].电测与仪表,2016,53(14):34-38,45,6.基金项目
四川省教育厅重点项目（13 ZA0023）；四川省电力电子节能技术与装备重点实验室项目（SZJJ2015－064）；太阳能技术集成及应用推广四川省高校重点实验室资金项目 （）
