基于多源域自适应残差网络的滚动轴承故障诊断

摘要
图/表
参考文献(37)
相关文章 (11)

全文: PDF (2281 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对传统无监督领域自适应方法扩展到多工况滚动轴承故障诊断场景适用性较弱的问题，提出了一种多源域自适应残差网络（Multi-source Domain Adaption Residual Network, MDARN），通过对齐来自多个源域的相关子域，从而提高模型在多工况下的故障诊断性能。首先，利用ResNeXt残差网络从源域和目标域充分提取可迁移特征;然后,引入局部最大平均差异(LMMD)准则，以两个源域的子域为基础对齐目标域中相关子域，减少相关子域间和全局域间的分布差异；最后，利用美国凯斯西储大学轴承数据集和MFS机械综合故障实验台产生的真实的轴承振动数据集，对所提方法进行了实验验证。结果表明，该方法在多工况下的平均故障诊断精度高达99.76%。与现有代表性方法相比，所提方法具有更好的故障诊断效果。

	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
	高学金1
	2
	3
	4
	张震华1
	2
	3
	4
	高慧慧1
	2
	3
	4
	齐咏生5

关键词 ：滚动轴承故障诊断, 多源域自适应残差网络, 领域自适应, 局部最大均值差异

Abstract：Aiming at the weak applicability of the traditional unsupervised domain adaptive method to multi-condition rolling bearing fault diagnosis scenarios, a Multi-source Domain Adaptive Residual Network (MDARN) was proposed. By aligning Correlated subdomains from multiple source domains, thus improving the fault diagnosis performance of the model under multiple operating conditions. First, the ResNeXt residual network is used to fully extract transferable features from the source domain and the target domain; then, the local maximum mean difference (LMMD) criterion is introduced to align the relevant subdomains in the target domain based on the subdomains of the two source domains, reducing The distribution difference between the relevant sub-domains and the global domain; finally, the proposed method is verified experimentally by using the bearing data set of Case Western Reserve University and the real bearing vibration data set generated by the MFS mechanical comprehensive fault test bench. The results show that the average fault diagnosis accuracy of this method is as high as 99.76% under multiple working conditions. Compared with the existing representative methods, the proposed method has better fault diagnosis effect.

Key words： fault diagnosis of rolling bearing Multi-source Domain Adaption Residual Network domain adaptation local maximum mean discrepancy

收稿日期: 2023-04-19 出版日期: 2024-04-15

引用本文:

高学金1，2，3，4,张震华1，2，3，4,高慧慧1，2，3，4,齐咏生5. 基于多源域自适应残差网络的滚动轴承故障诊断[J]. 振动与冲击, 2024, 43(7): 290-299.
GAO Xuejin1,2,3,4, ZHANG Zhenhua1,2,3,4, GAO Huihui1,2,3,4, QI Yongsheng5. Rolling bearing fault diagnosis based on multi-source domain adaptive residual network. JOURNAL OF VIBRATION AND SHOCK, 2024, 43(7): 290-299.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2024/V43/I7/290

[1] YAN Xiaoan, JIA Minping, ZHANG Wan, et al. Fault diagnosis of rolling element bearing using a new optimal scale morphology analysis method[J]. Isa Transactions, 2018, 73: 165-180. [2] IA Feng, LEI Yaguo, GUO Liang, et al. A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines[J]. Neurocomputing, 2018, 272(10): 619-628. [3] LU Siliang, HE Qingbo, ZHAO Jiwen, et al. Bearing fault diagnosis of a permanent magnet synchronous motor via a fast and online order analysis method in an embedded system[J]. Mechanical Systems and Signal Processing, 2017, 113(12): 36-49. [4] Report of large motor reliability survey of industrial and commercial installations: part 1, IEEE Trans. ia-23 4 (1987) 153–158. [5] Report of large motor reliability survey of industrial and commercial installations: part 3, IEEE Trans. ia-23 4 (1987) 153–158. [6] 李涛, 段礼祥, 张东宁, 赵赏鑫, 黄辉, 毕彩霞, 袁壮. 自适应卷积神经网络在旋转机械故障诊断中的应用[J]. 振动与冲击, 2020, 39(16): 275-282+288. Li Tao, DUAN Lixiang, ZHANG Dongning, et al. Application of adaptive convolutional neural network in rotating machinery fault diagnosis[J]. Journal of Vibration and Shock, 2020, 39(16): 275-282+288. [7] 吴静然, 丁恩杰, 崔冉, 刘建华. 采用多尺度注意力机制的旋转机械故障诊断方法[J]. 西安交通大学学报, 2020, 54(02): 51-58. WU Jingran, DING Enjie, CUI Ran, LIU Jianhua. A Diagnostic Approach for Rotating Machinery Using Multi-Scale Feature Attention Mechanism[J]. Journal of Xi'an Jiaotong University, 2020, 54(02): 51-58. [8] Alves D S, Daniel G B, de Castro H F, et al. Uncertainty quantification in deep convolutional neural network diagnostics of journal bearings with ovalization fault[J]. Mechanism and Machine Theory, 2020, 149: 103835. [9] 胡晓依, 荆云建, 宋志坤, 侯银庆. 基于CNN-SVM的深度卷积神经网络轴承故障识别研究[J]. 振动与冲击, 2019, 38(18): 173-178. HU Xiaoyi, JING Yunjian, SONG Zhikun, HOU Yinqing. Bearing fault identification by using deep convolution neural networks based on CNN-SVM[J]. Journal of Vibration and Shock, 2019, 38(18): 173-178. [10] 李益兵, 曹睿, 江丽. 基于稀疏滤波和长短期记忆网络的旋转机械故障诊断方法[J]. 振动与冲击, 2022, 41(19): 144-151+187. LI Yibing, CAO Rui, JIANG Li. Fault diagnosis method of rotating machinery based on spare filtering and lonf-short term memory network[J]. Journal of Vibration and Shock, 2022, 41(19): 144-151+187. [11] Li X, Ma H. Deep representation clustering-based fault diagnosis method with unsupervised data applied to rotating machinery[J]. Mechanical Systems and Signal Processing, 2020, 143: 106825. [12] 张超, 陈建军, 郭迅. 基EMD能量熵和支持向量机的齿轮故障诊断方法[J]. 振动与冲击, 2010, 29(10): 216-220+261. ZHANG Chao, CHEN Jianjun, GUO Xun. A gear fault diagnosis method based on EMD energy entropy and SVM[J]. Journal of Vibration and Shock, 2010, 29(10): 216-220+261. [13] Zeng N, Wang Z, Zhang H, et al. Deep belief networks for quantitative analysis of a gold immunochromatographic strip[J]. Cognitive Computation, 2016, 8: 684-692. [14] 雷亚国, 杨彬, 杜兆钧, 吕娜. 大数据下机械装备故障的深度迁移诊断方法[J]. 机械工程学报, 2019, 55(07): 1-8. LEI Yaguo, YANG Bin, DU Zhaojun, et al. Deep migration diagnosis method of mechanical equipment fault under big data[J]. Journal of Mechanical Engineering, 2019, 55 (07): 1-8. [15] Yang B, Lei Y, Jia F, et al. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings[J]. Mechanical Systems and Signal Processing, 2019, 122: 692-706. [16] Guo L, Lei Y, Xing S, et al. Deep convolutional transfer learning network: A new method for intelligent fault diagnosis of machines with unlabeled data[J]. IEEE Transactions on Industrial Electronics, 2018, 66(9): 7316-7325. [17] Li X, Zhang W, Xu N X, et al. Deep learning-based machinery fault diagnostics with domain adaptation across sensors at different places[J]. IEEE Transactions on Industrial Electronics, 2019, 67(8): 6785-6794. [18] Wen L, Gao L, Li X. A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J]. IEEE Transactions on systems, man, and cybernetics: systems, 2017, 49(1): 136-144. [19] Torralba A, Efros A A. Unbiased look at dataset bias[C]//CVPR 2011. IEEE, 2011: 1521-1528. [20] Zhu Y, Zhuang F, Wang J, et al. Deep subdomain adaptation network for image classification[J] IEEE transactions on neural networks and learning systems, 2020, 32(4): 1713-1722. [21] Zhuang F, Qi Z, Duan K, et al. A comprehensive survey on transfer learning[J]. Proceedings of the IEEE, 2020, 109(1): 43-76. [22] Pan S J, Tsang I W, Kwok J T, et al. Domain adaptation via transfer component analysis[J]. IEEE transactions on neural networks, 2010, 22(2): 199-210. [23] Yang B, Lei Y, Jia F, et al. A polynomial kernel induced distance metric to improve deep transfer learning for fault diagnosis of machines[J]. IEEE Transactions on Industrial Electronics, 2019, 67(11): 9747-9757. [24] Han T, Liu C, Yang W, et al. Deep transfer network with joint distribution adaptation: A new intelligent fault diagnosis framework for industry application[J]. ISA transactions, 2020, 97: 269-281. [25] Li L, Wan Z, He H. Dual alignment for partial domain adaptation[J]. IEEE transactions on cybernetics, 2020, 51(7): 3404-3416. [26] Farajzadeh-Zanjani M, Hallaji E, Razavi-Far R, et al. Adversarial semi-supervised learning for diagnosing faults and attacks in power grids[J]. IEEE Transactions on Smart Grid, 2021, 12(4): 3468-3478. [27] Roy S, Krivosheev E, Zhong Z, et al. Curriculum graph co-teaching for multi-target domain adaptation[C] Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 5351-5360. [28] Zhao C, Shen W. A domain generalization network combing invariance and specificity towards real-time intelligent fault diagnosis[J]. Mechanical Systems and Signal Processing, 2022, 173: 108990. [29] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2015[J]. Google Scholar, 2015: 1-9. [30] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778. [31] Gretton A, Borgwardt K M, Rasch M J, et al. A kernel two-sample test[J]. The Journal of Machine Learning Research, 2012, 13(1): 723-773. [32] Zhu Y, Zhuang F, Wang J, et al. Deep subdomain adaptation network for image classification[J]. IEEE transactions on neural networks and learning systems, 2020, 32(4): 1713-1722. [33] Tzeng E, Hoffman J, Zhang N, et al. Deep domain confusion: Maximizing for domain invariance[J]. arXiv preprint arXiv:1412.3474, 2014. [34] Long M, Cao Y, Wang J, et al. Learning transferable features with deep adaptation networks[C]/International conference on machine learning. PMLR, 2015: 97-105. [35] Zhu Y, Zhuang F, Wang D. Aligning domain-specific distribution and classifier for cross-domain classification from multiple sources[C]//Proceedings of the AAAI conference on artificial intelligence. 2019, 33(01): 5989-5996. [36] Zhu Y, Zhuang F, Wang J, et al. Multi-representation adaptation network for cross-domain image classification[J]. Neural Networks, 2019, 119: 214-221. [37] Xie S, Girshick R, Dollár P, et al. Aggregated residual transformations for deep neural networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1492-1500.