基于动态变步长果蝇算法优化支持向量机的轴承故障诊断方法  

A Fault Diagnosis Method Based on SVM Optimized by Improved Fruit Fly Optimization Algorithm

作　　者：谭晶晶[1] TAN Jingjing(School of Information Engineering,Zhengzhou Tourism College,Zhengzhou 223003,China)

机构地区：[1]郑州旅游职业学院信息工程学院,郑州450000

出　　处：《机械设计与研究》2021年第1期102-105,110,共5页Machine Design And Research

基　　金：河南省重点研发与推广专项支持项目(182102110277)。

摘　　要：针对果蝇算法(FOA)在优化支持向量机(SVM)参数时容易陷入局部最优而影响诊断精度的问题,对果蝇算法中固定步长这一缺点进行改进,提出了动态变步长果蝇算法(DCFOA)。利用该算法对支持向量机的参数进行优化,并对轴承的故障进行诊断,结果表明该算法获得了更优的支持向量机参数组合,相比于果蝇算法,显著提升了故障诊断精度,同时和其他一些优化算法的对比结果也表明动态变步长果蝇算法同样具有一定的优势。Aiming at the problem that the fruit fly optimization algorithm(FOA)is prone to fall into local optimum when optimizing the parameters of support vector machine(SVM)which will affect the diagnosis accuracy,a dynamic change step fruit fly optimization algorithm is proposedUsing the improved algorithm to optimize the parameters of support vector machine and used to fault diagnosis of bearing,the results show that the algorithm can obtained better parametersCompared with the fruit fly optimization algorithm,the accuracy of fault diagnosis are significantly improvedAt the same time,comparison results with some other optimization algorithm also show that the method is also has a certain advantage.

关 键 词：动态变步长 果蝇算法 支持向量机 故障诊断 轴承 

分 类 号：TH1653[机械工程—机械制造及自动化]