基于PSO优化的RBF网络液压泵故障诊断研究

提出了以小包分解和粒子群优化的径向基神经网络(RBFNN)为基础的液压泵故障诊断方法。通过小波包分解对振动信号做降噪处理并提取相应的故障信号的特征能量值,将此特征能量值作为神经网络的输入,再采用粒子群算法对神经网络的数据中心和宽度、输出权值和阈值进行优化,并将其分别与基于传统神经网络和基于遗传算法优化的故障诊断方法进行对比分析。对比结果表明,该方法具有很好的诊断效果。

Hydraulic Pump Fault Diagnosis of RBF Network Based on PSO Optimization

A fault diagnosis method is proposed based on wavelet packet analysis and PSO optimizing neural networks. The fault signal should be eliminated noise and extracted characteristic values as the input of neural network corresponding the fault signal. The data center and width, the output weights and thresholds are optimized by the particle swarm optimization. And compared with traditional neural network fault diagnosis method and genetic intelligent optimization algorithm optimizing the neural network fault diagnosis method, the results show that this method has high fault diagnosis rate.