小波神经网络故障预后模型的建立及其工程应用

故障诊断技术面临两大难题 ,第一如何“测量”故障的发育 ,第二如何预测一个有故障的机器或构件还能正常运行多久。本文用小波基函数神经网络技术解决了这两大课题。首先建立了小波基函数神经网络故障预后模型 ,用高斯基函数和Marr小波函数作为尺度函数 ,基函数中心的计算用二进展开函数和k次聚类函数。诊断实践表明 ,当轴承内表面产生间隙以后 ,应用训练后的小波基函数神经网络能够成功地对其间隙的发育进行预测。

Establishment of Fault Prognosis Model Using Wavelet Neural Networks and Its Engineering Application

Fault diagnosis confronted with two problems. Ho w to "measure" the growth of a fault and how to predict the remaining useful lifet ime of such a failing component or machine? This paper attempts to solve these t wo problems using wavelet basis neural networks. We first propose a model of fau lt prognosis using wavelet basis neural network. Gaussian radial basis functions and Mexican hat wavelet frames are used as scaling functions and wavelets respe ctively. The centers of the basis functions are calculated using a dyadic expans ion scheme and a k -means clustering algorithm. An example is presented in w hich a trained wavelet basis function neural network successfully prognose a def ective bearing with a crack in its inner race.