Focusing on the non-stationary characteristics of the fault signal of train auxiliary inverter,this paper proposes a method which based on local mean decomposition(LMD)and probabilistic neural network(PNN)to analyze original non-stationary signal.The non-stationary signal can be decomposed into multiple product function(PF)components by local mean decomposition(LMD)of the collected train fault signals.Theprobabilistic neural network(PNN)model is used to detect and classify fault signals.According to the sim...