Fault Diagnosis of Small Sample Automobile Planetary Gearboxes Based on Continuous Wavelet Transform and Model Agnostic Meta Learning

Xinxin Lu; Jun Ma; Yingcong Zhang

doi:10.16578/j.issn.1004.2539.2022.09.022

您当前的位置：

首页 >

文章列表页 >

Fault Diagnosis of Small Sample Automobile Planetary Gearboxes Based on Continuous Wavelet Transform and Model Agnostic Meta Learning

Development·Application | 更新时间：2022-09-26

- Fault Diagnosis of Small Sample Automobile Planetary Gearboxes Based on Continuous Wavelet Transform and Model Agnostic Meta Learning
- Journal of Mechanical Transmission Vol. 46, Issue 9, Pages: 159-164(2022)
- 作者机构：
  
  1.江苏工程职业技术学院航空与交通工程学院，江苏南通 226000
  2.江苏省智能网联汽车工程技术研究开发中心，江苏南通 226000
- 作者简介：
- 基金信息：
- DOI：10.16578/j.issn.1004.2539.2022.09.022
  CLC：
扫描看全文
卢欣欣,马骏,张英聪.基于连续小波变换和无模型元学习的小样本汽车行星齿轮箱故障诊断[J].机械传动,2022,46(09):159-164.

Lu Xinxin,Ma Jun,Zhang Yingcong.Fault Diagnosis of Small Sample Automobile Planetary Gearboxes Based on Continuous Wavelet Transform and Model Agnostic Meta Learning[J].Journal of Mechanical Transmission,2022,46(09):159-164.
卢欣欣,马骏,张英聪.基于连续小波变换和无模型元学习的小样本汽车行星齿轮箱故障诊断[J].机械传动,2022,46(09):159-164. DOI： 10.16578/j.issn.1004.2539.2022.09.022.

Lu Xinxin,Ma Jun,Zhang Yingcong.Fault Diagnosis of Small Sample Automobile Planetary Gearboxes Based on Continuous Wavelet Transform and Model Agnostic Meta Learning[J].Journal of Mechanical Transmission,2022,46(09):159-164. DOI： 10.16578/j.issn.1004.2539.2022.09.022.

摘要

针对行星齿轮箱振动信号具有较强的非平稳特性、故障样本少以及传统深度学习对数据依赖性的问题，提出了一种基于连续小波变换（Continuous wavelet transform，CWT）和无模型元学习（Model agnostic meta learning，MAML）的小样本行星齿轮箱故障诊断方法。通过CWT将行星齿轮箱振动信号转换为时频图像，有效地表达行星齿轮箱非平稳性特征；利用MAML“学会学习”的能力训练小样本的时频图像，对“未见过”的行星齿轮箱故障类型进行测试。通过对不同样本数量、跨工况条件和不同噪声环境下的行星齿轮箱进行故障诊断实验，结果表明，该方法相比于其他方法具有更高的识别精度、泛化性和鲁棒性。

Abstract

Aiming at the problem that the vibration signal of planetary gearboxes has strong non-stationary characteristics， few fault samples and the dependence of traditional deep learning on data， an intelligent diagnosis method for planetary gearboxes based on continuous wavelet transform（CWT） and model agnostic meta learning（MAML） is proposed. First， the vibration signal of the planetary gearbox is converted into a time-frequency image through CWT， which effectively expresses the non-stationary characteristics of the planetary gearbox； then， the ability of “learning to learn” of MAML is used to train small samples of time-frequency images， and finally the “unseen” faults of planetary gearboxes are tested. Through fault diagnosis experiments of planetary gearboxes under different sample sizes， working conditions and noise environments， a conclusion is drawn that the proposed method has higher recognition accuracy， generalization and robustness compared with other methods.

关键词

行星齿轮箱连续小波变换无模型元学习小样本学习故障诊断

Keywords

Planetary gearboxesContinuous wavelet transformModel agnostic meta learningFew shot learningFault diagnosis

references

杨世锡，尚小林，柳亦兵，等.大型旋转机械状态监测与故障诊断研究进展［J］.振动、测试与诊断，2015，35（1）：1-11.

YANG Shixi，SHANG Xiaolin，LIU Yibing，et al.State of the art of state monitoring and fault diagnosis for large rotating machinery［J］.Journal of Vibration，Measurement ＆ Diagnosis，2015，35（1）：1-11.

赵磊，郭瑜，伍星.基于包络加窗同步平均的行星齿轮箱特征提取［J］.振动、测试与诊断，2019，39（2）：320-326.

ZHAO Lei，GUO Yu，WU Xing.Feature extraction of planetary gearboxes based on windowed synchronous average of envelope signal［J］.Journal of Vibration，Measurement ＆ Diagnosis，2019，39（2）：320-326.

褚福磊，彭志科，冯志鹏.机械故障诊断中的现代信号处理方法［M］.北京：科学出版社，2009：21-53.

CHU Fulei，PENG Zhike，FENG Zhipeng.Modern signal processing methods in mechanical fault diagnosis［M］.Beijing：Science China Press Ltd.，2009：21-53.

ZHU Z K，YAN R，LUO L，et al.Detection of signal transients based on wavelet and statistics for machine fault diagnosis［J］.Mechanical Systems and Signal Processing，2009，23（4）：1076-1097.

ZHEN D，WANG Z，LI H，et al.An improved cyclic modulation spectral analysis based on the CWT and its application on broken rotor bar fault diagnosis for induction motors［J］.Applied Sciences，2019，9（18）：3902.

WANG J，HE Q，KONG F.Multiscale envelope manifold for enhanced fault diagnosis of rotating machines［J］.Mechanical Systems and Signal Processing，2015，52（1）：376-392.

李恒，张氢，秦仙蓉，等.基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法［J］.振动与冲击，2018，37（19）：124-131.

LI Heng，ZHANG Qing，QIN Xianrong，et al.Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network［J］.Journal of Vibration and Shock，2018，37（19）：124-131.

VERSTRAETE D，FERRADA A，LOPEZ D E，et al.Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings［J］.Shock and Vibration，2017（6）：1-17.

SHAO S，McALEER S，YAN R，et al.Highly accurate machine fault diagnosis using deep transfer learning［J］.IEEE Transactions on Industrial Informatics，2019，15（4）：2446-2455.

孙灿飞，王友仁.直升机行星传动轮系故障诊断研究进展［J］.航空学报，2017，38（7）：111-124.

SUN Canfei，WANG Youren.Advance in study of fault diagnosis of helicopter planetary gear［J］.Acta Aeronautica et Astronautica Sinica，2017，38（7）：111-124.

ZHANG S，YE F，WANG B，et al.Few-shot bearing anomaly detection based on model-agnostic meta-learning［J］.ArXiv Preprint ArXiv，2020（7）：1341-1346.

FINN C，ABBEEL P，LEVUNE S.Model-agnostic meta-learning for fast adaptation of deep networks［J］.ArXiv Preprint ArXiv，2017，70：1126-1135.

YAN R，GAO R X，CHEN X.Wavelets for fault diagnosis of rotary machines：a review with applications［J］.Signal Processing，2014，96：1-15.

LIN J，QU L.Feature extraction based on morlet wavelet and its application for mechanical fault diagnosis［J］.Journal of Sound and Vibration，2000，234（1）：135-148.

LE T P，ARGOUL P.Continuous wavelet transform for modal identification using free decay response［J］.Journal of Sound and Vibration，2004，277（1/2）：73-100.

TANG B，LIU W，SONG T.Wind turbine fault diagnosis based on morlet wavelet transformation and wigner-ville distribution［J］.Renewable Energy，2010，35（12）：2862-2866.

GLOROT X，BORDES A，BENGIO Y.Deep sparse rectifier neural networks［J］.Journal of Machine Learning Research，2011：315-323.

IOFFE S，SZEGEDY C.Batch normalization：accelerating deep network training by reducing internal covariate shift［J］.ArXiv Preprint ArXiv，2015，37：448-456.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Bearing Feature Extraction Method Based on the Time Subsequence

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

Research on Fault Diagnosis Method of Planetary Gearboxes Based on DPD-1DCNN

Review on Fault Diagnosis Technology for High-speed EMU Gearboxes

Research on Gear Early Wear Fault Diagnosis Based on the Sparse Attention Mechanism

Related Author

No data

Related Institution

School of Information Management, Wuxi Institute of Communications Technology

IOT Engineering College, Wuxi City College of Vocational Technology

State Key Laboratory of Traction Power, Southwest Jiaotong University

School of Rail Transportation, Wuyi University

College of Mechanical and Vehicle Engineering, Taiyuan University of Technology

⁰