针对采煤机在正常工作中经常发生轴承故障的问题,提出了小波包和BP神经网络相结合的故障诊断系统。即运用小波包的分解方法提取检测信号的故障信息作为BP神经网络的输入样本,经过训练的神经网络可对采煤机上轴承的工作状态进行诊断和分类。试验结果表明,此方法对轴承的常见故障可进行有效的识别和诊断,方法简单可靠。 Aiming at the bearing failure of the shearer in normal work, a fault diagnosis system based on wavelet packet and BP neural network is proposed. That is, the wavelet packet decomposition method is used to extract the fault information of the detection signal as the input sample of the BP neural network. The trained neural network can diagnose and classify the working status of the bearing on the shearer. The test results show that this method can effectively identify and diagnose the common faults of bearing, and the method is simple and reliable.