基于深度度量学习的轴承故障诊断方法

摘要
图/表
参考文献(21)
相关文章 (15)

全文: PDF (2013 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对机械大数据因故障类内离散度和类间相似度较大而导致诊断精度低的问题，提出一种深度度量学习故障诊断方法，采用深度神经网络(Deep neural network, DNN)对故障特征进行自适应提取，并利用基于欧氏距离的边际Fisher分析(Marginal fisher analysis, MFA)方法进行了优选，然后在构建的深度度量网络(Deep metric network, DMN)顶层特征输出层添加BPNN(Back propagation neural network, BPNN)分类器对网络参数进行微调，并实现故障的分类识别。最后，通过对不同类型和严重程度的轴承故障进行了诊断分析，验证了该方法可以有效地对轴承故障进行高精度诊断，效果优于传统深度信念网络(Deep belief network, DBN)故障诊断方法以及常用时域统计特征结合支持向量机(Support vector machine, SVM)分类的故障诊断方法。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李小娟1
	2
	徐增丙1
	2
	熊文3
	王志刚1
	2
	谭俊杰1
	2

关键词 ：深度度量学习, 轴承, 故障诊断, 相似度

Abstract：As the intra-class scatter and inter-class similarity are big in bearing fault data, which constrains the diagnostic accuracy, a new method of deep metric learning for fault diagnosis is proposed. The deep neural network (DNN) is used to adaptively extract the fault features, and the marginal Fisher analysis method based on Euclidean distance is used to optimize the features, then, the BPNN classifier is added to the top-level feature output layer of the constructed deep metric network (DMN) to fine tune the parameters and realize fault classification and recognition. Finally, diagnostic analysis on bearing fault experimental data of different fault types and different fault severity verified that the method can effectively diagnose bearing faults with high precision and the effect is better than traditional deep belief network (DBN) fault diagnosis method as well as the common time-domain statistical features combined with support vector machine (SVM) classification fault diagnosis method.

Key words： deep metric learning bearing fault diagnosis similarity

收稿日期: 2019-04-08 出版日期: 2020-07-28

引用本文:

李小娟1,2,徐增丙1,2,熊文3,王志刚1,2,谭俊杰1,2. 基于深度度量学习的轴承故障诊断方法[J]. 振动与冲击, 2020, 39(15): 25-31.
LI Xiaojuan1,2, XU Zengbing1,2, XIONG Wen3, WANG Zhigang1,2, TAN Junjie1,2. Bearing fault diagnosis method based on deep metric learning. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(15): 25-31.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2020/V39/I15/25

[1] Wang D, Tse P W, Tsui K L. An enhanced Kurtogram method for fault diagnosis of rolling element bearings[J]. Mechanical Systems and Signal Processing, 2013, 35(1-2):176-199.
[2] 雷亚国,贾峰,周昕,林京.基于深度学习理论的机械装备大数据健康监测方法[J].机械工程学报, 2015,51(21):49-56.
LEI Yaguo, JIA Feng, ZHOU Xi, LIN Jing. A Deep Learning-based Method for Machinery Health Monitoring with Big Data[J]. Journal of Mechanical Engineering, 2015, 51(21): 49-56
[3] 苏鑫,吴迎亚,裴华健,蓝兴英,高金森.大数据技术在过程工业中的应用研究进展[J].化工进展,2016,35(6):1652-1659.
SU Xin, WU Yingya, PEI Huajian, LAN Xingying, GAO Jinsen. Recent Development of The Application of Big Data Technology in Process Industries. Chemical Industry and Engineering Process, 2016, 35(6): 1652-1659.
[4] HOPKINS B, EVELSON B, LEAVER S, et al. Expand Your Digital Horizon with Big Data[R]. Forrester, 2011.
[5] Tamilselvan, P, Wang P. Failure Diagnosis Using Deep Belief Learning Based Health State Classification[J]. Reliability Engineering & System Safety, 2013, 115:124-135.
[6] 李巍华,单外平,曾雪琼.基于深度信念网络的轴承故障分类识别[J].振动工程学报,2016,29(2):340—347.
LI Weihua, SHAN Waiping, ZENG Xueqiong. Bearing Fault Identification Based on Deep Belief Network[J]. Journal of Vibration Engineering, 2016, 29(2): 340—347.
[7] J Olivier Janssens, Viktor Slavkovikj, Brain Vervisch.et a1. Convolutional Neural Network Based Fault Detection for Rotating Machinery[J]. J of Sound and Vibration,2016(337)331-345.
[8] 智洪欣,于洪涛,李邵梅,高超，王艳川.一种基于深度度量学习的视频分类方法[J].电子与信息学报,2018(11).
ZHI Hongxin, YU Hongtao, LI Shaomei, GUO Chao, WANG Yanchuan. A Deep Metric Learning Based Video Classification Method[J]. Journal of Electronics and Information Technology, 2018(11).
[9] Wu B, Chen Z, Wang J, et al. Exponential Discriminative Metric Embedding in Deep Learning[J]. Neurocomputing, 2018, 290.
[10] Hu J, Lu J, Tan Y P. Discriminative Deep Metric Learning for Face Verification in the Wild[C]. Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. IEEE, 2014.
[11] Hu J, Lu J, Tan Y P. Deep Transfer Metric Learning[C]. IEEE Conference on Computer Vision & Pattern Recognition.2015.
[12] Song H O, Xiang Y, Jegelka S, et al. Deep Metric Learning via Lifted Structured Feature Embedding[J]. 2015.
[13] I. W. Tsang, J. T. Kwok, C. Bay, and H. Kong. Distance Metric Learning with Kernels. In ICANN, pages 126–129,2003.
[14] D.-Y. Yeung and H. Chang. A Kernel Approach for Semi-supervised Metric Learning.TNN,18(1):141–149,2007.
[15] Lu J, Hu J, Jie Z. Deep Metric Learning for Visual Understanding: An Overview of Recent Advances[J]. IEEE Signal Processing Magazine, 2017, 34(6):76-84.
[16] Yan S, Xu D, Zhang B, et al. Graph Embedding: A General Framework for Dimensionality Reduction[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2007,29(1):40.
[17] H. Yu and J. Yang. A Direct LDA Algorithm for High Dimensional Data-with Application to Face Recognition Pattern Recognition, vol.34, pp.2067-2070,2001.
[18] Hinton GE, Osindero S, The Y-W. A Fast Learning Algorithm for Deep Belief Nets[J]. Neural Computation, 2006, 18(7):1527-1554.
[19] The Case Western Reserve University Bearing Data Center. Bearing Data Center Fault Test Data [EB/OL] (1998-10-04). http://csegroups.case.edu/bearingdatacenter/pages/download-data-file.
[20] Sokolova M, Japkowicz N, Szpakowicz S. Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation[J]. 2006.
[21] Van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008; 9:2580-2605.