基于小波包特征熵的飞机液压系统故障诊断方法研究

Research of Fault Diagnosis of Aircraft Hydraulic System Based on Wavelet Packet-Characteristic Entropy

为精确诊断飞机液压系统故障,提出了一种基于小波包特征熵的神经网络故障诊断新方法。对采集到的飞机液压系统压力信号进行小波包分解,提取小波包特征熵,然后构造信号的小波包特征熵向量,并以此向量作为故障样本,利用ART1神经网络进行训练,实现智能化故障诊断。试验结果表明,训练成功的ART1网络能够很好地诊断出飞机液压系统是否发生故障,为飞机液压系统故障诊断开辟了新的途径。

To diagnose accurately the fault of aircraft hydraulic system, this paper presents a new method of fault diagnosis based on wavelet packet and neural network. It adopts wavelet packet to decompose the monitored pressure signal of aircraft hydraulic system, ex tracts WP--CE （Wavelet Packet--Characteristic Entropy）, and constructs WP--CE vectors of signals, then takes those vectors as fault samples to ART1 （Adaptive Resonance Theory） neural network, finally realizes intelligent fault diagnosis. The practical example shows the trained ART1 neural network can diagnose the fault of aircraft hydraulic system. This method develops a new direction for the fault diagnosis of aircraft hydraulic system.