装甲车辆电源系统智能故障诊断方法研究

摘要

针对电源系统建模复杂的问题,通过Matlab/simulink建立装甲车辆电源系统仿真模型,应用小波包能量法提取电源系统在各种状态下电压及电流信号的能量特征向量,并将其作为故障分类器的输入向量;结合SOM神经网络无监督聚类和BP网络有监督学习的能力,构建两层的故障分类器对各种故障状态进行识别和诊断;以车辆电源系统中整流桥故障为例进行仿真分析,结果表明该方法具有快速准确的故障诊断能力.%Aiming at the problem of armored vehicles power system model setting, the simulate model is built in Matlab/simulink. These signal vectors of various states about voltage and current of power system, which are extracted by using the wavelet packet energy method, are integrated as the input vectors of the failure classifier, setting the failure classifier that has the ability of SOM with unsupervised clustering and BP with supervised study to identify and diagnose the various failure states. The simulate experiment with the rectifier bridge failure of vehicles power system as an example, shows that the method can diagnose fault rapidly and accurately.