Fault diagnosis method of bearing under cross working conditions based on substructure optimal transmission

PDF(2821 KB)

Journal of Vibration and Shock ›› 2023, Vol. 42 ›› Issue (7) : 273-280.

ZHU Liangyu, CUI Qianwen, HU Chaofan, HE Shuilong

Author information +

History +

Abstract

Aiming at the problems of inconsistent distribution of bearing vibration data under different working conditions, under-adaptation and over-adaptation in the adaptive process of the source domain and target domain, a fault diagnosis method based on substructure optimal transport for bearings under different working conditions is proposed. First, the fault features in the bearing vibration data are extracted through wavelet transform, and the fault sample set is constructed. Then cluster the bearing fault sample sets in the source domain and the target domain to generate a substructure of the source domain and target domain fault sample data. And adaptively assign different weights to the data substructure of the source domain, and assign the same weight to the data substructure of the target domain to complete the mapping of the data substructure of the source domain. Finally, using the mapped source domain data substructure and its corresponding labels, the support vector machine model is trained and the fault diagnosis of the bearing under the target working condition is realized through the trained model. The proposed method is verified on the mechanical comprehensive fault simulation experimental platform and the bearing dataset of Case Western Reserve University, and compared with traditional machine learning and other transfer learning methods. The experimental results show the effectiveness and superiority of the method.

Key words

fault diagnosis / substructure level matching / transfer learning / across working conditions

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

ZHU Liangyu, CUI Qianwen, HU Chaofan, HE Shuilong. Fault diagnosis method of bearing under cross working conditions based on substructure optimal transmission[J]. Journal of Vibration and Shock, 2023, 42(7): 273-280

References

[1] Lia Q, Wang Y, Xu Y. Synchrosqueezing extracting transform and its application in bearing fault diagnosis under non-stationary conditions[J]. Measurement, 2021, 173: 108569.
[2] 胡超凡,王衍学.基于张量分解的滚动轴承复合故障多通道信号降噪方法研究[J].机械工程学报,2019, 55(12):50-57.
HU Chao-fan, WANG Yan-xue. Research on multi-channel signal denoising method for multiple faults diagnosis of rolling element bearings based on tensor factorization[J]. Journal of Mechanical Engineering, 2019, 55(12):50-57.
[3] Zhou Z, Tan Y, Xie Y, et al. State estimation of a compound non-smooth sandwich system with backlash and dead zone[J]. Mechanical Systems and Signal Processing, 2017, 83: 439-449.
[4] Li X, Shao H, Lu S, et al. Highly Efficient Fault Diagnosis of Rotating Machinery Under Time-Varying Speeds Using LSISMM and Small Infrared Thermal Images[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022.
[5] Li Y, Yang Y, Wang X, et al. Early fault diagnosis of rolling bearings based on hierarchical symbol dynamic entropy and binary tree support vector machine[J]. Journal of Sound and Vibration, 2018, 428: 72-86.
[6] 王波,刘树林,张宏利,等.相关向量机及其在机械故障诊断中的应用研究进展[J].振动与冲击,2015, 34(05):145-153+167.
WANG Bo, LIU Shu-lin, ZHANG Hong-li, et al. Advances about relevance vector machine and its applications in machine fault diagnosis[J]. Journal of Vibration and Shock, 2015, 34(05):145-153+167.
[7] Hu C, Wang Y, Gu J. Cross-domain intelligent fault classification of bearings based on tensor-aligned invariant subspace learning and two-dimensional convolutional neural networks[J]. Knowledge-Based Systems, 2020, 209: 106214.
[8] An J, Ai P. Deep domain adaptation model for bearing fault diagnosis with Riemann metric correlation alignment[J]. Mathematical Problems in Engineering, 2020, 2020.
[9] Jia S, Wang J, Zhang X, et al. A Weighted Subdomain Adaptation Network for Partial Transfer Fault Diagnosis of Rotating Machinery[J]. Entropy, 2021, 23(4): 424.
[10] Wang X, Lu X, Song P, et al. A Novel Deep Learning Model for Mechanical Rotating Parts Fault Diagnosis Based on Optimal Transport and Generative Adversarial Networks[C]//Actuators. Multidisciplinary Digital Publishing Institute, 2021, 10(7): 146.
[11] Liu Z H, Jiang L B, Wei H L, et al. Optimal Transport-Based Deep Domain Adaptation Approach for Fault Diagnosis of Rotating Machine[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-12.
[12] Lu W, Chen Y, Wang J, et al. Cross-domain activity recognition via substructural optimal transport[J]. Neurocomputing, 2021, 454: 65-75.
[13] Villani C. Optimal transport: old and new[M]. Berlin: Springer, 2009.
[14] Peyre G, Cuturi M. Computational optimal transport: With applications to data science[J]. Foundations and Trends® in Machine Learning, 2019, 11(5-6): 355-607.
[15] Courty N, Flamary R, Tuia D, et al. Optimal transport for domain adaptation[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 39(9): 1853-1865.
[16] 张焱,冯乔琦,黄庆卿,等.非负自编码网络基于部分特征表示的变工况滚动轴承状态识别[J].仪器仪表学报,2020,41(04):77-85.
Zhang Yan, Feng Qiao-qi, Huang Qing-qing, et al. Rolling bearing state recognition under variable condition using part-based representation of non-negativity constrained autoencoder networks[J]. Chinese Journal of Scientific Instrument, 2020,41(04):77-85.
[17] 李栋,刘树林,孙欣.针对不连续时变样本空间的连续学习故障诊断方法[J].机械工程学报,2021,57(01):157-167.
LI Dong, LIU Shu-lin, SUN Xin. A continual learning fault diagnosis method for discontinuous time-varying sample space[J]. Journal of Mechanical Engineering, 2021, 57(01): 157-167.
[18] Chen C, Li Z, Yang J, et al. A cross domain feature extraction method based on transfer component analysis for rolling bearing fault diagnosis[C]//2017 29Th chinese control and decision conference (CCDC). IEEE, 2017: 5622-5626.
[19] Lei P, Shen C, Zhu J, et al. A new transferable bearing fault diagnosis approach with adaptive manifold embedded distribution alignment[J]. Measurement Science and Technology, 2020, 32(3): 034004.
[20] Fernando B, Habrard A, Sebban M, et al. Unsupervised visual domain adaptation using subspace alignment[C]//Proceedings of the IEEE international conference on computer vision. 2013: 2960-2967.
[21] Van der Maaten L, Hinton G. Visualizing data using t-SNE[J]. Journal of machine learning research, 2008, 9(11).
[22] Smith W A, Randall R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study[J]. Mechanical systems and signal processing, 2015, 64: 100-131.