«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

34

期数:

2024年05期

页码:

175-182

栏目:

新型计算应用系统

出版日期:

2024-05-10

文章信息/Info

Title:

Rolling Bearing Fault Diagnosis Method Based on Improved SSA Optimized SVM

文章编号:

1673-629X(2024)05-0175-08

作者:

唐浩漾; 王亦凡; 秦波; 李哲

西安邮电大学 自动化学院,陕西 西安 710121

Author(s):

TANG Hao-yang; WANG Yi-fan; QIN Bo; LI Zhe

School of Automation,Xi’an University of Posts and Telecommunications,Xi’an 710121,China

关键词:

故障诊断; 滚动轴承; 支持向量机; 改进麻雀搜索算法; 樽海鞘觅食机制

Keywords:

fault diagnosis; rolling bearing; support vector machine; improved sparrow search algorithm; foraging mechanisms of bottlenose sea squirt

分类号:

TP181

DOI:

10.20165/j.cnki.ISSN1673-629X.2024.0057

摘要:

针对支持向量机分类模型在滚动轴承故障诊断中准确率较低的问题,提出了一种基于改进麻雀搜索算法(Sparrow Search Algorithm,SSA)优化支持向量机(Support Vector Machine,SVM)的滚动轴承故障诊断方法。 首先,利用小波变换对滚动轴承信号进行去噪处理,将去噪后的信号进行小波包分解以提取对应故障特征;其次,引入改进樽海鞘觅食机制对麻雀搜索算法进行优化,防止算法向原点收敛,并加入自适应莱维飞行策略和精英反向系数,增强算法跳出局部最优的能力;最后,采用改进后的麻雀算法优化支持向量机参数,构建改进 SSA 优化 SVM 的故障诊断模型,提高故障分类效果。 应用美国西储大学提供的轴承数据集进行仿真实验,实验结果表明,所提方法的故障诊断效果好于 PSO-SVM、GWO-SVM、SSA-SVM、tSSA-SVM 等常规模型,能有效提取滚动轴承故障特征,具有较高的故障诊断精度。

Abstract:

Aiming at the problem of low accuracy of support vector machine classification model in rolling bearing fault diagnosis,a rolling bearing fault diagnosis method based on the improved SSA algorithm optimized support vector machine is proposed. Firstly,the wavelet transform is used to denoise the rolling bearing signals,and the denoised signals are decomposed into wavelet packets to extract the corresponding fault features. Secondly,the sparrow search algorithm is optimized by introducing an improved sea squirt foraging mechanism to prevent the algorithm from converging to the origin,and adaptive Levy flight strategy and elite inversion coefficients are added to enhance the ability of the algorithm to jump out of local optimums. Finally,the improved sparrow algorithm is used to optimize the parameters of the support vector machine to construct a fault diagnosis model with improved SSA-optimized SVM to improve the fault classification effect. Simulation experiments are carried out by applying the bearing dataset provided by Western Reserve University in the USA. The experimental results show that the fault diagnosis effect of the proposed method is better than that of the conventional models such as PSO-SVM,GWO-SVM,SSA-SVM,tSSA-SVM, etc. ,and it can effectively extract the fault characteristics of the rolling bearings with high fault diagnosis accuracy.

常用功能

更新日期/Last Update: 2024-05-10