基于GrC-NN和DS证据理论的电动汽车故障诊断

Fault diagnosis of electric vehicles based on GrC-NN and DS evidence theory

文章针对电动汽车故障数据庞杂、非线性的问题,提出了一种基于粒计算神经网络(granular computation-neural network,GrC-NN)和Dempster-Shafer(DS)证据理论的电动汽车故障诊断方法。该方法采用GrC对电动汽车故障信息进行属性约简,使用约简后的样本训练反向传播(back propagation,BP)神经网络与径向基函数(radial basis function,RBF)神经网络,并将测试数据输入到神经网络中分别进行初步诊断,最后利用DS证据理论对初步诊断结果进行决策级融合,得到最终诊断结果。仿真结果表明,该方法能有效简化神经网络结构,提高电动汽车故障诊断的准确度。

A fault diagnosis method for electric vehicles based on granular computation-neural network(GrC-NN)and Dempster-Shafer(DS)evidence theory is proposed to solve the problem of complex and nonlinear fault data of electric vehicles.In this method,the attributes of fault data samples of electric vehicles are reduced by GrC,then back propagation(BP)neural network and radial basis function(RBF)neural network are trained with the reduced samples,and the test data are input to the neural network for preliminary diagnosis.Finally,using DS evidence theory,the preliminary diagnosis results are fused at decision level and the final diagnosis results are obtained.Simulation results show that this method can effectively simplify the neural network structure and improve the accuracy of electric vehicle fault diagnosis.