BF及模糊神经网络在旋转机械故障诊断中的应用

本文对模糊神经网络用于故障诊断较传统BP(Back-Propagation)网络的优越性进行了分析,并提出了一种利用模糊神经网络进行旋转机械故障诊断的新方法。在这种方法中利用RBF(Radial Basis Function)神经网络获得隶属度函数,并简化了模糊神经网络的训练,使得新的故障诊断专家知识更易于扩充到现有的故障诊断网络中。仿真结果表明,本文方法所构建的故障诊断网络易于扩展且有良好的诊断效果。

Fault Diagnosis of Rotating Machinery Using RBF and Fuzzy Neural Network

The advantages of fuzzy neural network in the fault diagnosis application compared with traditional BP (Back-Propagation) neural network are discussed. A new diagnosis method based on fuzzy logic neural network is proposed. In this method, membership functions are got by using RBF (Radial Basis Function) neural network and the train load is reduced at the same time. The expertise knowledge newly obtained can be easily added to the diagnosis system. Simulation results show that the method in this paper has good performance.