RBF神经网络在整流器故障诊断中的应用  

Application of Radical Basis Function Neural Network in Fault Diagnosis of Rectifier

作　　者：谢永成[1] 董今朝[2] 李光升[2] 魏宁[2] 

机构地区：[1]装甲兵工程学院外训系,北京100072 [2]装甲兵工程学院控制工程系,北京100072

出　　处：《计算机测量与控制》2013年第12期3184-3186,3203,共4页Computer Measurement &Control

摘　　要：径向基函数(Radical Basis Function,RBF)神经网络是一种三层前向网络,它能够任意精度逼近任意连续函数,特别适合于解决分类问题;文章根据装甲车辆电源系统硅整流器故障早期多为单个二极管故障的特点,结合二极管因出现短路后会在很短时间内转化为开路故障的实际情况,首先利用MATLAB编程对建立的整流器模型进行数据采集,然后利用RBF神经网络进行网络训练和验证,从而将故障确定到具体的二极管,达到了对整流器故障诊断的目的;通过与BP神经网络的对比,结果表明RBF网络具有更强的分类能力。The Radical Basis Function（RBF）neural network is a kind of three-forward neural network,which can approximate any continuous functions to arbitrary precision,particularly suited to solve classification problems.In this paper,according to that armored vehicle power system silicon rectifier prophase fault is single diode and diode short-circuit fault in a very short period of time turned into the situation of the open-circuit fault,first,the rectifier model is established for data collection by MATLAB programming,then,make full use of the characteristics of the RBF network for network training and validation,in this way,determining the fault to a specific diode.It achieves the aim at fault diagnosis of rectifier.Comparing with BP neural network,RBF neural network has better classification ability.

关 键 词：RBF神经网络 整流器 故障诊断 

分 类 号：TN461[电子电信—微电子学与固体电子学]