Wasserstein Distance-EEMD Enhanced Multi-Head Graph Attention Network for Rolling Bearing Fault Diagnosis Under Different Working Conditions

• Autorzy: Wang Xingbing , Yao Yunfeng , Gao Chen

Identyfikatory

DOI

10.17531/ein/184037

• Języki publikacji: EN

Abstrakty

EN

Traditional fault diagnosis models often overlook the interconnections between segments of vibration data, resulting in the loss of critical feature information. Additionally, the vibration signals of rolling bearings exhibit non-linear behaviors during operation. Therefore, an efficient fault diagnosis model tailored for rolling bearings is proposed in this paper. In the proposed model, the 1D vibration signals are first preprocessed using ensemble empirical mode decomposition (EEMD). This technique generates multiple intrinsic mode functions (IMF) as individual nodes. The percentage distance between each node is calculated using the Wasserstein distance (WD) to capture the relationships between nodes and use it as the edge weights to construct a node graph. This unique approach enhances the transformation of 1D vibration signals into a node graph representation, preserving important information. An improved multi-head graph attention network (MGAT) model is established to extract features and perform classification on the node graph. This MGAT model effectively utilizes the relationships between nodes and enhances the accuracy of fault diagnosis. The experimental results demonstrate that the proposed method achieves higher accuracy compared to similar modelswhile requiring less processing time. The proposed approach contributes significantly to the field of fault diagnosis for rolling bearings and provides a valuable tool for practical applications.

Słowa kluczowe

EN

ensemble empirical mode decomposition; Wasserstein distance; multi head graph attention Network; fault diagnosis; rolling bearing

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2024
• Tom: Vol. 26, no. 2
• Strony: art. no. 184037
• Opis fizyczny: Bibliogr. 26 poz., rys., tab., wykr.

Twórcy

autor

Wang Xingbing

• College of Mechanical and Electrical Engineering, Wenzhou University, China

autor

Yao Yunfeng

• College of Mechanical and Electrical Engineering, Jiaxing Nanhu University, China

autor

Gao Chen

• School of Mechanical and Transportation, Jiaxing Nanyang Polytechnic Institute, China

Bibliografia

• 1. J. Lin, H.D. Shao, X.D. Zhou, B.P Cai, B. Liu. Generalized MAML for few-shot cross-domain fault diagnosis of bearing driven by heterogeneous signals. Expert Systems with Applications, 2023, 230, 120696.https://doi.org/10.1016/j.eswa.2023.120696
• 2. D. Liu, L.L. Cui, W. Cheng. Flexible generalized demodulation for intelligent bearing fault diagnosis under nonstationary conditions. IEEE Transactions on Industrial Informatics, 2023, 19(3): 2717-2728.https://doi.org/10.1109/TII.2022.3192597
• 3. Y.Q. Zhou, W. Sun, C.Y. Ye, B.H. Peng, X.X. Fang, C. Lin, G.H. Wang, A. Kumar, W.F. Sun.Time-frequency Representation -enhanced Transfer Learning for Tool Condition Monitoring during milling of Inconel 718. Eksploatacja i Niezawodnosc –Maintenance and Reliability 2023: 25(2), 165926.https://doi.org/10.17531/ein/165926
• 4. D. Liu, L.L. Cui, W. Cheng. A review on deep learning in planetary gearbox health state recognition: Methods, applications, and dataset publication. Measurement Science and Technology, 2023, https://doi.org/10.1088/1361-6501/acf390
• 5. Z.D.Hei, B.T.Sun, G.H.Wang, Y.J.Lou, Y.Zhou. Multi-feature spatial distribution alignment enhanced domain adaptive method for tool condition monitoring. Eksploatacja i Niezawodnosc-Maintenance and Reliability, 2023: 25(4). https://doi.org/10.17531/ein/171750
• 6. Y.Q. Zhou, G.F. Zhi, W. Chen, Q.J. Qian, D.D. He, B.T. Sun, W.F. Sun. A New Tool Wear Condition Monitoring Method Based on Deep Learning under Small Samples.Measurement, 2022,189, 110622.https://doi.org/10.1016/j.measurement.2021.110622
• 7. S. Yan, H.D. Shao, J. Wang, X.Y. Zheng, B. Liu. LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attention. ExpertSystems with Applications, 2024,237, 121338.https://doi.org/10.1016/ j.eswa.2023.121338
• 8. H.C.Wang, W.Sun, W.F.Sun, Y.Ren, Y.Q.Zhou, Q.J.Qian, A.Kumar. A novel tool condition monitoring based on Gramian angular field and comparative learning. International Journal of Hydromechatronics, 2023, 6(2): 93-107. https://doi.org/10.1504/IJHM.2023.130510
• 9. J. Zhao, S.P. Yang, Q. Li, Y.Q. Liu, X.H. Gu, W.P. Liu. A new bearing fault diagnosis method based on signal-to-image mapping and convolutional neural network. Measurement. 2021, 176,109088. https://doi.org/10.1016/j.measurement.2021.109088
• 10. DChen, R. Liu, Q. Hu, S.X. Ding. Interaction-Aware Graph Neural Networks for Fault Diagnosis of Complex Industrial Processes. IEEE Trans Neural Netw Learn Syst. 2023, 34(9):6015-6028. https://doi.org/10.1109/TNNLS.2021.3132376
• 11. Y.Q.Zhou, H.C.Wang, G.H.Wang, A.Kumar, W.F.Sun, J.W.Xiang. Semi-Supervised Multiscale Permutation Entropy-Enhanced Contrastive Learning for Fault Diagnosis of Rotating Machinery. IEEE Transactions on Instrumentation and Measurement, 2023, 72, 3525610. https://doi.org/10.1109/TIM.2023.3301051
• 12. Z. Wang, Z.Y. Wu, X.Q. Li, H.D. Shao, T. Han, M. Xie.Attention-aware temporal–spatial graph neural network with multi-sensor information fusion for fault diagnosis. Knowledge-Based Systems. 2023, 10,110891.https://doi.org/10.1016/j.knosys.2023.110891
• 13. Z.HYuan, X.Li, S.YLiu,Z.Q.Ma.A recursive multi-head graph attention residual network for high-speed train wheelset bearing fault diagnosis. Measurement Science and Technology. 2023, 34(6). https://doi.org/10.1088/1361-6501/acb609
• 14. Y.Q. Zhou, A. Kumar, C Parkash, G. Vashishtha, H.S.Tang, J.W.Xiang.A novel entropy-based sparsity measure for prognosis of bearing defects and development of a sparsogram to select sensitive filtering band of an axial piston pump.Measurement, 2022, 203, 111997.https://doi.org/10.1016/j.measurement.2022.111997
• 15. G.X.Zheng, W.Chen, Q.J.Qian, A.Kumar, W.F.Sun, Y.Q. Zhou. TCM in milling processes based on attention mechanism-combined long short-term memory using a sound sensor under different working conditions. International Journal of Hydromechatronics, 2022, 5(3): 243-259.https://doi.org/10.1504/IJHM.2022.125090
• 16. N.E. Huang, Z. Shen, S.R. Long. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society. A, Mathematical, physical, and engineering sciences. 1998, 454:903-995. https://doi.org/10.1098/rspa.1998.0193
• 17. Z.K. Peng, P.W. Tse, F.L. Chu. A comparison study of improved Hilbert–Huang transform and wavelet transform: Application to fault diagnosis for rolling bearing. Mechanical Systems & Signal Processing, 2005, 19(5): 974-988. https://doi.org/10.1016/j.ymssp.2004.01.006
• 18. X. Yin, L.Y. Fu.Decorrelation EMD:A new method to eliminate modal aliasing. Vibration and Shock. 2015, 34(4):25-29.https://doi.org/10.13465/j.cnki.jvs.2015.04.005
• 19. Y.G.Lei, D.T. Kong, N.P.Li, J. Lin. Adaptive overall average empirical mode decomposition and its application to planetary gearbox fault detection. Journal of Mechanical Engineering. 2014, 50(03). PP 64-70. https://doi.org/10.3901/JME.2014.03.064
• 20. Z.H. Wu, N.E. Huang.Ensemble empirical mode decomposition: a noise-assisted data analysis method. Advances in Adaptive Data Analysis. 2009, 1(1): 1-41. https://doi.org/10.1142/S1793536909000047
• 21. H.K.Jiang, C.L.Li, H.X.Li. An improved EEMD with multiwavelet packet for rotating machinery multi-fault diagnosis. Mechanical Systems and Signal Processing. 2013, 36(2):225-239. https://doi.org/10.1016/j.ymssp.2012.12.010
• 22. V.M.Panaretos, Y.Zemel. Statistical Aspects of Wasserstein Distances. Annual Review of Statistics and Its Application. 2019, 6(1):405-431.https://doi.org/10.1146/annurev-statistics-030718-104938
• 23. P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, Y. Bengio.Graph attention networks. International Conference on Learning Representations(ICLR) 2018.
• 24. J. Li, J.R. Wang, H. Lv, Z.X. Zhang, Z.X. Wang. IMCHGAN: Inductive Matrix Completion With Heterogeneous Graph Attention Networks for Drug-Target Interactions Prediction. IEEE/ACM transactions on computational biology and bioinformatics, 2022,19(2): 655-665. https://doi.org/10.1109/TCBB.2021.3088614
• 25. J.H. Holland. Adaptation in Natural and Artificial Systems:An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence.The MIT Press, Cambridge, Massachusetts, London, England, 1992.https://doi.org/10.7551/mitpress/1090.001.0001
• 26. Ya Guo L, Tian Yu H, Biao W, et al. Interpretation of XJTU-SY rolling bearing accelerated life test data set. Journal of Mechanical Engineering. 2019, 55(16):1-6. https://doi.org/10.3901/JME.2019.16.001