基于参数优化的DBO-VMD-SVM滚动轴承故障诊断  

DBO-VMD-SVM Rolling Bearing Fault Diagnosis Based on Parameter Optimization

作　　者：胡洋腾 买买提热依木·阿布力孜[1] 张超 史文杰 HU Yang-teng;Maimaitireyimu Abulizi;ZHANG Chao;SHI Wen-jie(College of Electrical Engineering,Xinjiang University,Urumqi Xinjiang,830017,China)

机构地区：[1]新疆大学电气工程学院,新疆乌鲁木齐830017

出　　处：《计算机仿真》2025年第1期466-472,共7页Computer Simulation

基　　金：国家自然科学基金项目(62163034)。

摘　　要：针对滚动轴承故障诊断中存在的算法参数难以选择、诊断准确率较低等问题,提出一种用蜣螂优化算法(DBO)优化变分模态分解(VMD)和支持向量机(SVM)参数的故障诊断方法。首先,通过DBO对VMD的分解层数和惩罚因子进行寻优,以最小包络熵为目标函数,寻找最优参数组合。其次,利用DBO-VMD将原始振动信号分解为若干个本征模态函数,计算每个分量的样本熵并构造特征向量。最后将构造的特征向量输入到DBO-SVM故障诊断模型中进行训练和测试。仿真结果表明,上述方法在滚动轴承故障分类方面分类效果好、诊断准确率高,相较于其它优化方法具有收敛速度快、优化能力强的特点。Aiming at the problems of difficult selection of algorithm parameters and low diagnostic accuracy in rolling bearing fault diagnosis.A fault diagnosis method using Dung Beetle Optimizer(DBO)to optimize the parameters of Variable Mode Decomposition(VMD)and Support Vector Machine(SVM)is proposed.Firstly,the DBO algorithm is used to optimize the decomposition layers and penalty factor of VMD,and the minimum envelope entropy is taken as the objective function to find the optimal parameter combination.Secondly,the original vibration signal is decomposed into several intrinsic mode functions using DBO-VMD,the sample entropy of each component is calculated,and feature vectors are constructed.Finally,the constructed feature vectors are input into the DBO-SVM fault diagnosis model for training and testing.The simulation experimental results show that the proposed method has a good classification effect and high diagnostic accuracy in rolling bearing fault classification,and has the characteristics of fast convergence speed and strong optimization ability compared with other optimization methods.

关 键 词：故障诊断 滚动轴承 支持向量机 蜣螂优化 变分模态分解 

分 类 号：TP202.7[自动化与计算机技术—检测技术与自动化装置]