基于模糊神经网络的滚动轴承滑动擦伤诊断

Skidding Scrape Diagnosis of Rolling Bearing Based on Fuzzy Neural Network

针对故障诊断知识模糊性及引起轴承滑动擦伤的参数间的非线性特点 ,提出了基于模糊神经网络的故障诊断方法 ,建立了模糊神经网络模型 ,并将其应用于滚动轴承的滑动擦伤诊断。网络测试结果表明 。

An effective control of the skidding scrape for a rolling bearing can reduce its waste rate. The paper briefly analyzed the shortcomings of the conventional skidding scrape diagnosis of rolling bearings based on the statistical properties of parameters, generally speaking, which could only be applied in the diagnosis of faults classified linearly. For the fuzzy properties of fault diagnostic knowledge and the non linearity of the parameters describing skidding scrapes of a rolling bearing, we developed a fault diagnosis method based on fuzzy neural network. The modal of fuzzy neural network was established for the use of skidding scrape diagnosis of rolling bearings. The testing results were analyzed and discussed, and showed that the method in this paper is efficient for the fault diagnosis of skidding scrape of rolling bearing.