VMD及PSO优化SVM的行星齿轮箱故障诊断

被引：28

作者：

刘秀丽 ^{[1
]}

王鸽 ^{[1
]}

吴国新 ^{[1
]}

李相杰 ^{[2
]}

机构：

[1] 北京信息科技大学现代测控技术教育部重点实验室

[2] 华锐风电科技(集团)股份有限公司

来源：

电子测量与仪器学报 | 2022年 / 36卷 / 01期

基金：

国家重点研发计划;

关键词：

行星齿轮箱; 故障特征凸显; PSO优化SVM; 适应度函数; 样本熵;

D O I：

10.13382/j.jemi.B2104376

中图分类号：

TH132.41 [齿轮及齿轮传动];

学科分类号：

082805 [农业机械化与装备工程];

摘要：

以故障高发的行星齿轮传动系统为对象，提出基于变分模态分解(variational mode decomposition, VMD)及粒子群算法(particle swarm optimization, PSO)优化支持向量机(support vector machine, SVM)的故障诊断方法。首先，对信号进行VMD分解，采用改进小波降噪的方法处理分解后的本征模态分量(IMF),并对处理后的分量进行重构，凸显信号蕴含的信息；然后，对处理后的振动信号进行特征提取，分别提取信号的样本熵和均方根误差，并组成输入矩阵；最后，引入PSO优化SVM的关键参数，将提取的特征向量输入PSO-SVM进行训练和识别。将该方法应用于行星传动试验平台获取的行星轮裂纹故障、太阳轮轮齿故障及行星轮轴承故障信号，通过多维比较，验证了该方法的有效性。

引用

页码：54 / 61

页数：8

共 17 条

[1]

Data-driven time-frequency analysis method based on variational mode decomposition and its application to gear fault diagnosis in variable working conditions.[J].Fuhao Li;Rong Li;Lili Tian;Lin Chen;Jian Liu.Mechanical Systems and Signal Processing.2019,

[2]

Amplitudes of characteristic frequencies for fault diagnosis of planetary gearbox.[J].Mian Zhang;KeSheng Wang;Dongdong Wei;Ming J. Zuo.Journal of Sound and Vibration.2018,

[3]

Diagnosis methodology for identifying gearbox wear based on statistical time feature reduction [J].

Jose Saucedo-Dorantes, Juan ;

Delgado-Prieto, Miguel ;

Alfredo Osornio-Rios, Roque ;

de Jesus Romero-Troncoso, Rene .

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE, 2018, 232 (15) :2711-2722

[4]

A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing.[J].Xiaoan Yan;Minping Jia.Neurocomputing.2018,

[5]

An intelligent fault diagnosis approach for planetary gearboxes based on deep belief networks and uniformed features [J].

Wang, Xin ;

Qin, Yi ;

Zhang, Aibing .

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2018, 34 (06) :3619-3634

[6]

A fault diagnosis scheme for planetary gearboxes using adaptive multi-scale morphology filter and modified hierarchical permutation entropy.[J].Yongbo Li;Guoyan Li;Yuantao Yang;Xihui Liang;Minqiang Xu.Mechanical Systems and Signal Processing.2018,

[7]

基于多通道加权卷积神经网络的齿轮箱振动信号特征提取 [J].