基于小波包和PSO-Elman神经网络的滚动轴承故障诊断

针对滚动轴承的故障诊断，分析滚动轴承故障机理及特点，提出基于小波包分析的滚动轴承振动信号的特征向量提取算法，并建立PSO-Elman神经网络进行故障诊断和识别。将滚动轴承故障振动信号进行小波包分解，构造频带能量谱作为特征向量，输入PSO-Elman神经网络对故障进行识别。试验结果表明，基于小波包分析和PSO-Elman神经网络相结合的方法可准确地实现滚动轴承的故障诊断。

Rolling Bearing Fault Diagnosis Using Wavelet Packet Analysis and PSO-Elman Neural Network

For the fault diagnosis of rolling bearing , the paper analyses the mechanism and characteristics of rolling bearing faults,presents an algorithm based on wavelet packet analysis of rolling bearing vibration signal feature vector extraction,and establishes the PSO-Elman neural network for fault diagnosis and identification.Wavelet package decomposition is performed for the fault vibration signal of the rolling bearing.The frequency band energy spectrum serves as the feature vector. It was input to the PSO-Elman neural network for fault identification.The test results show that the method based on the wavelet packet analysis and PSO-Elman neural network can accurately achieve the rolling bearing fault diagnosis.