基于参数优化BP神经网络的数控机床主轴承故障诊断

Fault Diagnosis of Main Bearing of CNC Machine Tool Based on Parameter Optimization BP Neural Network

为进一步提高数控机床主轴承故障诊断精度,提出基于参数优化BP神经网络的数控机床主轴承故障诊断方法,利用麻雀搜索算法优化网络中所有的权值和阈值,改善网络在诊断过程中容易出现的收敛困难和陷入局部极值问题。首先,用小波包分解方法对采集的振动加速度信号进行处理,提取轴承故障能量特征值,再利用优化后的BP神经网络进行故障诊断。采用美国凯斯西储大学滚动轴承数据对该改进算法加以检验,实验结果表明,经参数优化后BP神经网络的诊断精度可达0.997,较优化前提升了0.384,具有很好的诊断效果。

In order to further improve the fault diagnosis accuracy of the main bearing of CNC machine tools,a fault diagnosis method of the main bearing of CNC machine tools based on parameter optimization BP neural network is proposed.The sparrow search algorithm is used to optimize all the weights and thresholds in the network,so as to improve the convergence difficulties and local extreme value problems that are easy to occur in the diagnosis process of the network.Firstly,wavelet packet decomposition method is used to process the collected vibration acceleration signal,extract the bearing fault energy eigenvalue,and then the optimized BP neural network is used for fault diagnosis.The improved algorithm is tested with the rolling bearing data of Case Western Reserve University.The experimental results show that the diagnosis accuracy of BP neural network after parameter optimization can reach 0.997,which is 0.384 higher than that before optimization,and has a good diagnosis effect.