Application of Deep Support Vector Machine in Gear Fault Diagnosis

Lei Yu; Sen Chen; Rui Zhang; Ke Li; Lei Su

doi:10.16578/j.issn.1004.2539.2019.08.028

您当前的位置：

首页 >

文章列表页 >

Application of Deep Support Vector Machine in Gear Fault Diagnosis

Development·Application | 更新时间：2022-09-25

- Application of Deep Support Vector Machine in Gear Fault Diagnosis
- Journal of Mechanical Transmission Vol. 43, Issue 8, Pages: 150-156(2019)
- 作者机构：
  
  1.江南大学机械工程学院，江苏无锡 221000
  2.东华大学机械工程学院，上海 200000
- 作者简介：
- 基金信息：
- DOI：10.16578/j.issn.1004.2539.2019.08.028
  CLC：
扫描看全文
于磊,陈森,张瑞等.深度支持向量机在齿轮故障诊断中的应用[J].机械传动,2019,43(08):150-156.

Yu Lei,Chen Sen,Zhang Rui,et al.Application of Deep Support Vector Machine in Gear Fault Diagnosis[J].Journal of Mechanical Transmission,2019,43(08):150-156.
于磊,陈森,张瑞等.深度支持向量机在齿轮故障诊断中的应用[J].机械传动,2019,43(08):150-156. DOI： 10.16578/j.issn.1004.2539.2019.08.028.

Yu Lei,Chen Sen,Zhang Rui,et al.Application of Deep Support Vector Machine in Gear Fault Diagnosis[J].Journal of Mechanical Transmission,2019,43(08):150-156. DOI： 10.16578/j.issn.1004.2539.2019.08.028.

摘要

针对齿轮箱故障诊断中存在的早期非平稳微弱故障信号特征提取困难，易受强背景噪声干扰，故障诊断精度较低等问题，提出了一种基于变分模态分解（Variational Mode Decomposition，VMD）和深度支持向量机（Deep Support Vector Machine，DSVM）的齿轮箱故障诊断方法。首先，利用VMD将原始振动信号分解成若干个频率尺度的本征模态（Intrinsic Mode Function，IMF）分量，并根据峭度最大准则选取IMF分量对信号进行重构；构建多层支持向量机结构，在输入层利用支持向量机对信号进行训练，学习信号的浅层特征，利用“特征提取公式”生成样本新的表示，并作为隐藏层的输入，逐层利用深层SVM对新样本训练并学习信号的深层特征，最终由输出层输出诊断结果。最后，通过齿轮箱故障诊断实验验证了该方法的有效性。

Abstract

Gearbox fault diagnosis has problems in early feature extraction of non-stationary weak fault signals, vulnerability to strong background noise, and low accuracy of fault diagnosis. A gearbox fault diagnosis method based on Variational Mode Decomposition（VMD）and Deep Support Vector Machine(DSVM) is proposed. Firstly, the original vibration signal is decomposed into several frequency scale Intrinsic Mode Function (IMF) components by VMD, and the IMF component is selected according to the maximum kurtosis criterion to reconstruct the signal. Secondly, the multi-layer support vector is constructed. The SVM is used to train the training sample on the input layer, and it learns the shallow features of the data. The feature extraction formula is used to generate a new expression of the sample, which is used as input of the hidden layer. The hidden layer of the SVM trains on the new sample, and it extracts and learns the deep features of the signal layer by layer, eventually, it outputs the diagnostic results on the output layer. The effectiveness of the proposed method is verified by the gearbox fault diagnosis experiment.

关键词

故障诊断变分模态分解峭度深度支持向量机齿轮箱

Keywords

Fault diagnosisVMDKurtosisDeep support vector machineGearbox

references

丁玉兰，石来德.机械设备故障诊断技术［M］.上海：上海科学技术文献出版社，1994：548-563.

AN Xueli，ZENG Hongtao，LI Chaoshun.Envelope demodulation based on variational mode decomposition for gear fault diagnosis［J］.Journal of Process Mechanical Engineering，2017，231（4）：864-870.

ZHAO Hongshan，LI Lang.Fault diagnosis of wind turbine bearing based on variational mode decomposition and Teager energy operator［J］.IET Renewable Power Generation，2017，11（4）：453-460.

马增强，李亚超，刘政，等.基于变分模态分解和Teager能量算子的滚动轴承故障特征提取［J］.振动与冲击，2016，35（13）：134-139.

刘永斌，何清波，孔凡让，等.基于PCA和SVM的内燃机故障诊断［J］.振动、测试与诊断，2012，32（2）：250-255.

马笑潇，黄席樾，柴毅.基于SVM的二叉树多类分类算法及其在故障诊断中的应用［J］.控制与决策，2003（3）：272-276.

王德文，雷倩.基于贝叶斯正则化深度信念网络的电力变压器故障诊断方法［J］.电力自动化设备，2018，38（5）：129-135.

王丽华，谢阳阳，周子贤，等.基于卷积神经网络的异步电机故障诊断［J］.振动.测试与诊断，2017，37（6）：1208-1215.

陈仁祥，黄鑫，杨黎霞，等.加噪样本扩展深度稀疏自编码神经网络的滚动轴承寿命阶段识别［J］.振动工程学报，2017，30（5）：874-882.

WANG Y，Markert R，XIANG J，et al.Research on variational mode decomposition and its application in detecting rub-impact fault of the rotor system［J］.Mechanical Systems & Signal Processing，2015，60/61：243-251.

DRAGOMIRETSKIY K，ZOSSO D.Variational mode decomposition［J］.IEEE Transactions on Signal Processing，2014，62（3）：531-544.

LI K，SU L，WU J，et al.A rolling bearing fault diagnosis method based on variational mode decomposition and an improved kernel extreme learning machine［J］.Applied Sciences-Basel，2017，7（10）：1004

TU X，HU Y，LI F，et al.Demodulated high-order synchrosqueezing transform with application to machine fault diagnosis［J］.IEEE Transactions on Industrial Electronics，2019，66（4）：3071-3081.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAP

Gearbox Fault Diagnosis Based on the LMD Cloud Model and PSO-KELM

Research on Gearbox Fault Diagnosis Based on LMD Energy Entropy

Gearbox Fault Diagnosis based on GAF-inceptionResNet

Gearbox Fault Diagnosis based on Time-frequency Combination Feature Extraction and Manifold Learning of MS-LTSA

Related Author

No data

Related Institution

State Key Laboratory of Traction Power, Southwest Jiaotong University

School of Rail Transportation, Wuyi University

School of Mechanical and Electrical Engineering, Xi'an Polytechnic University

Engineering Training Center, Jiangsu Normal University

School of Mechatronic Engineering, China University of Mining and Technology

⁰