基于BP神经网络和小波包能量熵的异步电动机故障诊断

Fault Diagnosis of Asynchronous Motor Based on BP Neural Network and Wavelet Packet Energy Analysis

为了高效解决异步电动机故障问题,提出了一种基于反向传播(BP)神经网络和小波包能量分析的异步电动机故障诊断系统。采用定子电流信号作为异步电动机的故障信号,运用小波包能量分析对采集的定子电流信号进行分析,提取出相应的故障特征向量。为了提高诊断的准确性,提取信号时域、频域的特征,输入到BP神经网络中进行训练学习。经过足够多的训练后,用测试样本对其精确率进行测试。通过所提方法,可以及时排除及修正异步电动机故障,提高工厂的经济效益。

In order to efficiently solve the problem of asynchronous motor fault, a fault diagnosis system of asynchronous motor based on back-propagation(BP) neural network and wavelet packet energy analysis is proposed. The stator current signal is used as the fault signal of asynchronous motor, and the collected stator current signal is analyzed by wavelet packet energy analysis to extract the corresponding fault feature vector. In order to improve the accuracy of diagnosis, the time-domain and frequency-domain features of signals are extracted and input into BP neural network for training and learning. After enough training, the accuracy is tested with test samples. Through the proposed method, the faults of asynchronous motor can be eliminated and corrected in time, and the economic benefits of the factory can be improved.