基于改进果蝇优化算法优化支持向量机的故障诊断  

A FAULT DIAGNOSIS METHOD BASED ON SUPPORT VECTOR MACHINE OPTIMIZED BY IMPROVED FRUIT FLY OPTIMIZATION ALGORITHM

作　　者：黄晓璐[1] 周湘贞[2] HUANG XiaoLu;ZHOU XiangZhen(Department of Public Science,Henan Vocational College Of Nursing,Anyang 455000,China;School of Information Engineering,ZhengZhou Shengda University of Economics,Business & Management,Zhengzhou 451191,China)

机构地区：[1]河南护理职业学院公共学科部,安阳455000 [2]郑州升达经贸管理学院信息工程学院,郑州451191

出　　处：《机械强度》2019年第3期568-574,共7页Journal of Mechanical Strength

基　　金：河南省科技攻关项目(182102110277)资助~~

摘　　要：为提高支持向量机(SVM)在机械故障诊断中的精度,对果蝇优化算法(FOA)进行改进,提取了一种基于改进果蝇优化算法优化SVM的故障诊断方法。改进果蝇优化算法(IFOA)中果蝇个体在进行位置更新时,融入了历史位置信息,在增加果蝇种群多样性的同时,又使算法具有了跳出局部最优的能力,进而可以获得更优的SVM参数以增强SVM分类性能。齿轮故障诊断实例验证了IFOA算法提升了SVM的识别效果,相比于其他一些方法更有优势。In order to improve diagnosis accuracy of support vector machine(SVM) in mechanical fault diagnosis,fruit fly optimization algorithm was improved and a fault diagnosis method based on SVM optimized by improved FOA was proposed.In improved FOA(IFOA),history location information was introduced when fruit fly update its location,thus improved diversity of fruit fly group and the ability of jump out local optimum and better parameters of SVM can be obtained and classification performance of SVM was improved.Gear fault diagnosis experiment results validated that IFOA improved the identification accuracy of SVM and has a certain superiority when compared with some other methods.

关 键 词：改进果蝇优化算法 参数优化 支持向量机 故障诊断 

分 类 号：TH165.3[机械工程—机械制造及自动化]