基于改进麻雀搜索算法优化SVM的轴承故障诊断研究  

Research on Bearing Fault Diagnosis Based on Improved Sparrow Search Algorithm to Optimize SVM

作　　者：文征 段俊勇[1] 杨化林[1] WEN Zheng;DUAN Junyong;YANG Hualin(Qingdao University of Science and Technology,Qingdao 266100)

机构地区：[1]青岛科技大学,青岛266100

出　　处：《舰船电子工程》2023年第9期151-155,233,共6页Ship Electronic Engineering

摘　　要：对于当前SVM分类能力受到自身参数影响较大的问题,提出一种基于改进麻雀搜索算法(ISSA)的故障诊断方法,对支持向量机进行优化。首先介绍了基本的麻雀搜索算法,之后使用高斯变异与Tent混沌映射将其进行优化改进,改进后的算法能够有效提升收敛速度,并且避免算法陷入局部最优解,增强算法的全局搜索能力。采用改良的麻雀搜索算法(ISSA),优化支持向量机的惩罚参数(C)和核参数(g),构建ISSA-SVM滚动轴承故障诊断模型。最终结果显示,ISSA-SVM诊断模型对滚动轴承正常状态和故障状态下的故障诊断准确率最高达100%,比改进前的麻雀搜索算法诊断模型(SSA-SVM)提高了1.81%,比粒子群优化算法诊断模型(PSO-SVM)提高了2.23%。For the current problem that the classification ability of SVM is greatly affected by its own parameters,a fault diagnosis method based on improved sparrow search algorithm(ISSA)is proposed to optimize the support vector machine.Firstly,the basic sparrow search algorithm is introduced,and then the Tent chaotic mapping and Gaussian variation are applied to the sparrow search algorithm for optimization to improve the convergence speed and global search ability of the algorithm,so as to avoid the algorithm from falling into the local optimal solution.The improved sparrow search algorithm(ISSA)is used to optimize the penalty parameters(C)and nuclear parameters(g)of the support vector machine to construct the ISSA-SVM rolling bearing fault diagnosis model.The final results show that the ISSA-SVM diagnostic model has up to 100% accuracy in troubleshooting in the normal and fault conditions of rolling bearings,which is 1.81% higher than the improved sparrow search algorithm diagnostic model(SSA-SVM)and 2.23% higher than the particle swarm optimization algorithm diagnostic model(PSO-SVM).

关 键 词：故障诊断 支持向量机 麻雀搜索算法 混沌映射 高斯变异 

分 类 号：TH133.33[机械工程—机械制造及自动化]