基于改进多尺度均值排列熵和参数优化SVM的齿轮箱故障诊断方法  

Gearbox Fault Diagnosis Method Based on Improved Multi-scale Mean Permutation Entropy and Parameter Optimization SVM

作　　者：郭盼盼 张文斌 崔奔 徐晗 Guo Panpan;Zhang Wenbin;Cui Ben;Xu Han(Faculty of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming 650500,China;School of Mechanical and Electrical Engineering,Kunming University,Kunming 650214,China)

机构地区：[1]昆明理工大学机电工程学院,云南昆明650500 [2]昆明学院机电工程学院,云南昆明650214

出　　处：《机械传动》2024年第4期154-161,共8页Journal of Mechanical Transmission

基　　金：国家自然科学基金项目(51769007);云南省地方本科高校基础研究联合专项重点项目(202001BA070001-002);兴滇英才支持计划项目经费支持(YNWR-QNBJ-2018-349);云南省地方高校联合专项面上项目(202001BA070001-015)。

摘　　要：当齿轮箱传动系统发生故障时,不同振动信号的多尺度均值排列熵(Multi-scale Mean Per⁃mutation Entropy,MMPE)与其故障状态有一定的对应关系,但MMPE提取故障特征的效果取决于参数的选取。因此,提出了一种基于改进MMPE和参数优化支持向量机(Support Vector Machine,SVM)的齿轮箱故障识别方法。首先,引用粒子群优化(Particle Swarm Optimization,PSO)算法对MMPE的参数进行优化;其次,对采集到的齿轮振动信号计算其MMPE;最后,采用PSO-SVM对齿轮的故障状态进行了识别。试验结果验证了所提方法的有效性且具有较高的准确率。When a gearbox transmission system fails,the multi-scale mean permutation entropy(MMPE)of different vibration signals corresponds to the fault state to a certain extent.However,the effect of multi-scale mean permutation entropy extraction fault features depends on the selection of parameters.Therefore,this study proposes a gearbox fault identification method based on the improved multi-scale mean permutation entropy and the parameter optimization support vector machine(SVM).Firstly,the particle swarm optimization(PSO)is ref-erenced to optimize parameters of multi-scale mean permutation entropy.Secondly,the multi-scale mean per-mutation entropy of the collected gear vibration signals is calculated.Finally,the particle swarm optimization is used to optimize the support vector machine to identify the fault state of the gear.Experimental analysis results are conducted to validate the effectiveness of this proposed method.

关 键 词：多尺度均值排列熵 粒子群优化算法 支持向量机 故障诊断 齿轮 

分 类 号：TH132.41[机械工程—机械制造及自动化] TP18[自动化与计算机技术—控制理论与控制工程]