融合多特征信息与GWO-SVM的机械关键设备故障诊断  

Fault Diagnosis of Key Equipment Machinery Based on Multi-Feature Information and GWO-SVM

作　　者：宋玲玲[1] 王琳 钟丽[2] 李晨曦 SONG Ling-ling;WANG Lin;ZHONG Li;LI Chen-xi(Department of Electrical and Electronic Engineering,Yantai Vocational College,Shandong Yantai 264670,China;School of Information and Electrical Engineering,Ludong University,Shandong Yantai 264670,China;School of Mechanical Engineering,Shandong University of Technology,Shandong Zibo 255000,China)

机构地区：[1]烟台职业学院电气与电子工程系,山东烟台264670 [2]鲁东大学信息与电气工程学院,山东烟台264670 [3]山东理工大学机械工程学院,山东淄博255000

出　　处：《机械设计与制造》2024年第11期116-121,共6页Machinery Design & Manufacture

基　　金：山东省2021年度职业教育教学改革研究项目(2021119)。

摘　　要：为了提高机械关键设备故障诊断的精度,建立机械关键设备故障诊断模型。文章提出一种融合机械关键设备故障信号多特征信息与灰狼优化算法(Grey Wolf Optimization Algorithm,GWO)改进支持向量机(Support Vector Machine,SVM)(GWO-SVM)的机械关键设备故障诊断模型。首先,提取机械关键设备故障信号的时域特征、频域特征和多尺度加权排列熵特征,分别对比不同特征的机械关键设备故障诊断结果。其次,为提高SVM模型性能,运用GWO算法对SVM模型的惩罚参数P和核函数参数g进行优化选择,提出一种融合多特征信息与GWO-SVM的机械设备故障诊断模型。与GA-SVM、PSO-SVM和SVM相比,基于GWO-SVM的机械设备故障诊断模型的诊断精度最高。这里算法可以有效提高机械关键设备故障诊断正确率,为机械关键设备故障诊断提供了新的方法。In order to improve the fault diagnosis accuracy of key equipment machinery,establish a fault diagnosis model of key equipment machinery.A fault diagnosis model for key equipment machinery is proposed by fusion of key equipment machinery multi-feature information and Grey Wolf Optimization Algorithm(GWO)improved Support Vector Machine(SVM)(GWOSVM).Firstly,extracting the time domain feature,frequency domain feature and multi-scale weighted permutation entropy feature of the fault signal of the key equipment machinery,and comparing the fault diagnosis results of the key equipment machinery with different characteristics.Secondly,in order to improve the performance of the SVM model,the GWO algorithm is used to optimize the selection of the SVM model parameters for the penalty parameter P and the kernel function parameter g,and key equipment machinery fault diagnosis model that combines multi-feature information and GWO-SVM is proposed.Compared with GASVM,PSO-SVM and SVM,the fault diagnosis model of key equipment machinery based on GWO-SVM has the highest diagnosis accuracy.The proposed methods can effectively improve the accuracy of the fault diagnosis of the key equipment machinery,and provide a new method for the fault diagnosis of the key equipment machinery.

关 键 词：时域特征 灰狼优化算法 支持向量机 频域特征 多尺度加权排列熵 

分 类 号：TH16[机械工程—机械制造及自动化] TP391[自动化与计算机技术—计算机应用技术]