基于JMFAN网络的跨轴承故障诊断

摘要
图/表
参考文献(22)
相关文章 (15)

全文: PDF (1743 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要工业生产中使用的电机轴承类型多种多样，由于数据标注成本高昂，往往存在某种型号的轴承缺乏带标签数据。针对上述问题，本文提出了一种用于无监督学习的联合多尺度特征自适应网络(Joint Multi-Scale Feature Adaptation Network，JMFAN)，使用联合最大均值差异算法度量不同领域之间的距离，通过最小化领域间联合概率分布实现跨轴承故障诊断。围绕不同型号轴承在不同工况下的故障展开迁移学习研究，并进行实验验证。结果表明，该方法相比于传统的无监督迁移学习方法，可以显著提高在不同轴承故障诊断中准确率和模型泛化能力，在凯斯西储大学轴承数据下八个不同迁移任务中平均准确率达到了99.06％。

	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
	刘智宏
	史丽萍
	陈凯玄
	陈瑞
	韩丽

关键词 ：迁移学习, 无监督学习, 领域自适应, 跨轴承故障诊断

Abstract：In industrial production, there are various types of motor bearings, and it is often the case that certain models of bearings lack labeled data due to the high cost of annotation. To address this issue, this paper proposes a Joint Multi-Scale Feature Adaptation Network (JMFAN) for unsupervised learning. The JMMD algorithm is utilized to measure the distance between different domains, and cross-bearing fault diagnosis is achieved by minimizing the joint probability distribution across domains. The research focuses on transfer learning concerning the faults of different models of bearings under different operating conditions, and experimental verification is conducted. The results demonstrate that compared to traditional unsupervised transfer learning methods, this approach significantly improves the accuracy and model generalization capability in different bearing fault diagnosis tasks. The average accuracy rate reaches 99.06% in eight different transfer tasks using the bearing data from Western Reserve University.

Key words： Transfer learning Unsupervised learning Domain Adaptation Cross bearing fault diagnosis

收稿日期: 2023-09-14 出版日期: 2024-06-15

引用本文:

刘智宏，史丽萍，陈凯玄，陈瑞，韩丽. 基于JMFAN网络的跨轴承故障诊断[J]. 振动与冲击, 2024, 43(11): 118-125.
LIU Zhihong, SHI Liping, CHEN Kaixuan, CHEN Rui, HAN Li. Cross-bearing fault diagnosis based on JMFAN. JOURNAL OF VIBRATION AND SHOCK, 2024, 43(11): 118-125.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2024/V43/I11/118

[1] 于春雨,张文韬,张庆海等.基于EMD-AR与改进宽度学习系统的滚动轴承故障诊断方法[J/OL].中国电机工程学报:1-13[2023-05-26]. YU Chunyu, ZHANG Wentao, ZHANG Qinghai,et al. Fault diagnosis method of a rolling bearing on EMD-AR and improved broad learning system [J/OL].Proceedings of the CSEE:1-13[2023-05-26]. [2] 邢晓松,郭伟.基于改进半监督生成对抗网络的少量标签轴承智能诊断方法[J].振动与冲击, 2022,41(22):184-192.DOI:10.13465/j.cnki.jvs.2022.22.022. XING Xiaosong, GUO Wei. Intelligent diagnosis method for bearings with few labelled samples based on an improved semi-supervised generative adversarial network[J]. Journal of Vibration and Shock, 2022,41(22):184-192.DOI:10.13465/j.cnki.jvs.2022.22.022. [3] 雷亚国,贾峰,孔德同等.大数据下机械智能故障诊断的机遇与挑战[J].机械工程学报,2018,54(05):94-104. LEI Yaguo, JIA Feng, KONG Detong, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering,2018,54(05):94-104. [4] 张西宁,郭清林,刘书语.深度学习技术及其故障诊断应用分析与展望[J].西安交通大学学报,2020,54(12):1-13. ZHANG Xining, GUO Qinglin, LIU Shuyu. Analysis and prospect of deep learning technology and its fault diagnosis application[J].Journal of Xi'an Jiaotong University,2020,54(12):1-13. [5] 杨洁,万安平,王景霖等.基于多传感器融合卷积神经网络的航空发动机轴承故障诊断[J].中国电机工程学报,2022,42(13):4933-4942.DOI:10.13334/j.0258-8013.pcsee.211097. YANG Jie, WAN Anping, WANG Jinglin, et al. Aeroengine bearing fault diagnosis based on convolutional neural network for multi-sensor information fusion[J].Proceedings of the CSEE, 2022,42(13):4933-4942.DOI:10.13334/j.0258-8013.pcsee.211097. [6] 张弘斌,袁奇,赵柄锡,牛广硕.采用多通道样本和深度卷积神经网络的轴承故障诊断方法[J].西安交通大学学报,2020,54(08):58-66. ZHANG Hongbin, YUAN Qi, ZHAO Bingxi, et al.Bearing fault diagnosis with multi-channel sample anddeep convolutional neural network[J].Journal of Xi'an Jiaotong University, 2020,54(08):58-66. [7] 车畅畅,王华伟,倪晓梅,蔺瑞管. 基于深度残差收缩网络的滚动轴承故障诊断[J]. 北京航空航天大学学报,2021,47(07):1399-1406. CHE Changchang, WANG Huawei, NI Xiaomei, et al.Fault diagnosis of rolling bearing based on deep residual shrinkage network[J].Journal of Beijing University of Aeronautics and Astronautics, 2021,47(07):1399- 1406. [8] Zhang A , Li S , Cui Y , et al. Limited data rolling bearing fault diagnosis with few-shot learning [J]. IEEE Access, 2019, PP(99):1-1. [9] 于春雨,张文韬,张庆海等.基于EMD-AR与改进宽度学习系统的滚动轴承故障诊断方法[J/OL].中国电机工程学报:1-13[2023-05-27].http://kns.cnki.net/kcms/detail/11.2107.TM.20220826.1642.012.html. YU Chunyu, ZHANG Wentao, ZHANG Qinghai,et al.Fault diagnosis method of a rolling bearing on EMD-AR and improved broad learning system[J/OL]. Proceedings of the CSEE: 1-13[2023-05-27].http://kns.cnki.net/kcms/detail/11.2107.TM.20220826.1642.012.html. [10] Zhou X , Xuyun F U , Zhao M , et al. Regression model for civil aero-engine gas path parameter deviation based on deep domain-adaptation with Res-BP neural network[J]. Chinese Journal of Aeronautics, 2020, 34(1). [11] 张西宁,余迪,刘书语.基于迁移学习的小样本轴承故障诊断方法研究[J].西安交通大学学报,2021,55(10):30-37. ZHANG Xining, YU Di, LIU Yushu. Fault diagnosis method for small sample bearing based on transfer learning[J].Journal of Xi'an Jiaotong University, 2021,55(10):30-37. [12] 雷春丽,薛林林,焦孟萱,张护强,史佳硕.结合改进ResNet与迁移学习的风力机滚动轴承故障诊断方法[J/OL].太阳能学报:1-10[2023-05-28].DOI:10.19912/j.0254-0096.tynxb.2022-0204. LEI Chunli, XUE Linlin, JIAO Mengxuan, et al.Fault diagnosis method of wind turbines rolling bearing based on improved resnet and transfer learning[J/OL]. Acta Energiae Solaris Sinica:1-10[2023-05-28].DOI:10.19912/j.0254-0096.tynxb.2022-0204. [13] Li F, Chen J, Pan J, et al. Cross-domain learning in rotating machinery fault diagnosis under various operating conditions based on parameter transfer[J]. Measurement Science and Technology, 2020, 31(8): 085104. [14] 王玉静,吕海岩,康守强,谢金宝,V.I.MIKULOVICH.不同型号滚动轴承故障诊断方法[J].中国电机工程学报,2021,41(01):267-276+416.DOI:10.13334/j.0258-8013.pcsee.201173. WANG Yujing, LYU Haiyan, KANG Shouqiang, et al.Fault diagnosis method for different types of rolling bearings[J]. Proceedings of the CSEE,2021,41(01):267-276+416.DOI:10.13334/j.0258-8013.pcsee.201173. [15] 贾峰,李世豪,沈建军,马军星,李乃鹏.采用深度迁移学习与自适应加权的滚动轴承故障诊断[J].西安交通大学学报,2022,56(08):1-10. JIA Feng, LI Shihao, SHEN Jianjun, et al. Fault diagnosis of rolling bearings using deep transfer learning and adaptive weighting[J]. Journal of Xi'an Jiaotong University, 2022,56(08):1-10. [16] Long M, Wang J. Learning Transferable Features with Deep Adaptation Networks[J]. JMLR.org, 2015. [17] M.Long,H.Zhu,J.Wang,and M.I.Jordan,“Deep transfer learning with joint adaptation networks,”in Proc.34th Int.Conf.Mach.Learn.,2017,pp.2208–2217. [18] YOSINSKI J, CLUNE J, BENGIO Y, et al. How transferable are features in deep neural networks[C]//Proceedings of the27th International Conference on Neural Information Processing Systems(NIPS).[S.l.]:[s.n.], 2014:3320-3328. [19] 陈凯,张礼华,赵恒等.基于深度特征提取和对抗域适应网络的滚动轴承故障诊断[J].制造技术与机床,2023,No.727(01):9-15.DOI:10.19287/j.mtmt.1005-2402.2023.01.001. CHEN Kai, ZHANG Lihua, ZHAO Heng, CHEN Jingming. Rolling bearing fault diagnosis based on depth feature extraction and domain-adversarial training of neural networks[J]. Manufacturing Technology & Machine Tool,2023,No.727(01):9-15.DOI:10.19287/j.mtmt.1005-2402.2023.01.001. [20] 陆振聪. 基于深度学习的高速铁路列车轮对轴承故障诊断方法研究[D].北京交通大学,2022.DOI:10.26944/d.cnki.gbfju.2022.000644. CHEN Zhencong. Research on fault diagnosis method of high-speed railway train wheel set bearing of based on Deep Learning[D]. Beijing Jiaotong University,2022.DOI:10.26944/d.cnki.gbfju.2022.000644. [21] Ganin Y , Lempitsky V . Unsupervised Domain Adaptation by Backpropagation[J]. JMLR.org, 2014. [22] Long M , Wang J . Learning Transferable Features with Deep Adaptation Networks[J]. JMLR.org, 2015.