基于小波变换和神经网络的航空发动机故障诊断

Aeroengine Fault Diagnosis Based on Wavelet Transform and Neural Network

摘要:

在阐述了小波变换和BP神经网络概念的基础上,根据小波神经网络故障诊断的基本思想,提出了一种基于“能量—故障”的小波预处理神经网络航空发动机诊断方法。实验仿真结果表明,使用该方法提取故障特征加快了神经网络的训练速度,能迅速地进行故障的诊断。

Abstract:

The aeroengine fault diagnosis method was presented, based on the basic idea of wavelet transform and neural network. The proposed method used wavelet transform as the preprocessor of BPNN. The result of simulation showed that the fault could be detected quickly and the training speed of BPNN was dramatically accelerated.