资 源 简 介
为检测和诊断电力电子电路中的故障，获得更高的诊断精确度，提出粒子群算法优化RBF神经网络的故障诊断方法。与基本RBF神经网络相比，粒子群RBF神经网络可以提高系统的收敛速度和精度。把通过特征提取获得的电力电子电路故障特征量作为神经网络的输入，利用训练好的粒子群优化后的RBF神经网络进行故障诊断。仿真结果表明，实际输出与期望输出基本吻合，具有良好的分类效果，能够提高诊断精确度，对于电力电子电路的故障诊断是一种有效的方法。
Abstract:
In order to detect and diagnose the fault on power electronic circuit and to get higher precision of diagnosis， this paper puts forward a method of power electronic circuit fault diagnosis by RBF neural network based on Particle Swarm Optimization（PSO）. Compared with the basic RBF neural network， it improves convergence speed of the system. Some fault characteristics through the feature extraction were selected as inputs neural network for training，and then the fault diagnosis was accomplished via the trained and optimized neural network. The experimental results show that the actual output as same as the expectation output and this method gains good classification results，and it can improve the precision of diagnose，this method is validity for power electronic circuit diagnosis.
