小波包神经网络在卸船机电机故障模式识别中的应用

针对卸船机中异步电机故障率高的问题,本文采用小波包分解和神经网络技术相结合的方式,将采集到的电机振动信号进行小波包分解,通过分析观测信号在小波包某一分解层次上不同时频分辨空间中的能量分布,进行电机运行状态的特征提取,对提取的特征用RBF神经网络技术进行故障诊断,为卸船机的电机故障诊断提供了一种新的思路和方法。

Motor Fault Pattern Recognition of Ship-unloader Based on Wavelet Package and Neural Network

In order to reduce the high fault rate occurring in the induction motor of the shipunloader , this paper presents a new method for motor fault diagnosis of the ship-unloader, which combines the technology of wavelet packet decomposing and nerve network technology. The principle is： first, decomposing the collected motor vibration signals through wave- let packet, then analyzing the energy distribution of the signals on the different time frequency space of a certain decomposed layer to obtain the characteristics of the motor on working status, and finally, carrying out the fault diagnosis on those characteristics by applying RBF nerve network technology.