基于小波BP网络的汽轮发电机组故障诊断

针对电厂汽轮发电机组故障诊断问题,将小波变换和BP网络结合构造了一个三层的小波BP网络故障诊断系统。在输入层对振动信号进行二进离散小波变换,提取其在多尺度下的细节系数作为故障特征向量,根据这些特征向量进行小波BP网络的学习,最后用该学习过的小波BP网络诊断故障并将此方法成功地应用于汽轮发电机组故障诊断。仿真结果表明此方法是可行和有效的。

Fault diagnosis of turbo-generator units based on wavelet BP networks

To solve the problems of fault diagnosis for turbo-generator units,a three-layer wavelet BP network which combines wavelet transform and BP network was constructed.The vibration signal is processed by discrete binary wavelet transform at the input layer,and the detail coefficients are obtained under multi-resolution as fault character vectors.The BP network is trained according to these character vectors,and the trained BP network diagnoses the fault finally.The method was successfully used to diagnose the fault for turbo-generator units and simulations show the method feasible and effective.