基于粒子群优化RBF神经网络轴承故障诊断研究  

Research on Bearing Fault Diagnosis Based on Particle Swarm Optimization RBF Neural Network

作　　者：郭阳恒 张永富[1] GUO Yangheng;ZHANG Yongfu(College of Mathematics and Physics,Inner Mongolia Minzu University,Tongliao Inner Mongolia 028000,China)

机构地区：[1]内蒙古民族大学数理学院,内蒙古通辽028000

出　　处：《信息与电脑》2023年第3期89-92,共4页Information & Computer

基　　金：国家自然科学基金项目(项目编号:11961053);内蒙古民族大学博士科研启动基金项目(项目编号:BS424)。

摘　　要：轴承是当代机械设备中一种重要零部件。轴承故障是机械设备故障的来源之一,因此对轴承故障的诊断研究具有重要意义。文章提出了一种基于粒子群优化径向基函数(Radial Basis Function,RBF)神经网络的算法,先用小波包分解将源信号分解成独立信号源,再构建独立特征值,将特征值输入RBF和改进后的RBF中识别故障。实验结论表明,改进后的算法有较好的故障诊断能力。Bearing is a necessary part of contemporary mechanical equipment,and the fault of bearing is also one of the fault sources of mechanical equipment,which has been of great significance to the fault diagnosis research.In this thesis,an algorithm based on particle swarm optimization Radial Basis Function(RBF)neural network is proposed,which uses wavelet packet decomposition to decompose the source signal into an independent signal source.Independent eigenvalues were constructed and input into RBF and the improved RBF for fault identification.Experimental results show that the improved algorithm has the ability to better diagnose fault.

关 键 词：小波包分解 径向基函数(RBF)神经网络 粒子群算法 故障诊断 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]