Abstract
Rolling bearings, as integral components of rotating machinery, play a crucial role in ensuring the safe and stable operation of equipment. However, due to the inherent imbalance in the collected actual data, the accuracy of fault diagnosis is significantly compromised. An enhanced relative generative adversarial network (ERGAN) data augmentation model is proposed to improve fault diagnosis capability in imbalanced datasets. This paper introduces a relative loss function with a gradient penalty to enhance training stability and effectively address the mode collapse issue. Additionally, the generator and discriminator are reconstructed using one-dimensional convolutional layers and spectral normalization layers, which improves the quality of generated samples and effectively avoid gradient issues. Finally, an improved deep convolutional diagnostic model (DCNN) is established using variable convolutional kernels for fault classification. Experimental results demonstrate that, compared to other methods, this approach exhibits superior performance in imbalanced fault diagnosis tasks.
Similar content being viewed by others
References
R. Liu, B. Yang, E. Zio and X. Chen, Artificial intelligence for fault diagnosis of rotating machinery: A review, Mech. Syst. Signal Process, 108 (2018) 33–47.
H. Ren, W. Liu, M. Shan and X. Wang, A new wind turbine health condition monitoring method based on VMD-MPE and feature-based transfer learning, Measurement, 148 (2019) 106906.
Z. W. Gao, C. Cecati and S. X. Ding, A survey of fault diagnosis and fault-tolerant techniques—part II: fault diagnosis with knowledge-based and hybrid/active approaches, IEEE Transactions on Industrial Electronics, 62(6) (2015) 3768–3774.
J. Wang et al., Batch-normalized deep neural networks for achieving fast intelligent fault diagnosis of machines, Neurocomputing, 329(15) (2019) 53–65.
J. Zhu et al., Application of recurrent neural network to mechanical fault diagnosis: A review, Journal of Mechanical Science and Technology, 36(2) (2022) 527–542.
Y. Li et al., Automated and adaptive ridge extraction for rotating machinery fault detection, IEEE/ASME Transactions on Mechatronics, 28(5) (2023) 2565–2575.
Y. Li et al., Time-frequency ridge estimation: An effective tool for gear and bearing fault diagnosis at time-varying speed, Mechanical Systems and Signal Processing, 189 (2023) 110108.
H. Yi, Q. Jiang, X. Yan and B. Wang, Imbalanced classification based on minority clustering synthetic minority oversampling technique with wind turbine fault detection application, IEEE Transactions on Industrial Informatics, 17(9) (2020) 5867–5875.
X. Zhang et al., Rotating machinery fault diagnosis for imbalanced data based on decision tree and fast clustering algorithm, J. of Vibroengineering, 19(6) (2017) 4247–4259.
Q. Zhou et al., A novel method based on nonlinear autoregression neural network and convolutional neural network for imbalanced fault diagnosis of rotating machinery, Measurement, 161 (2020) 107880.
I. Goodfellow et al., Generative adversarial networks, Communications of the ACM, 63(11) (2020) 139–144.
P. Mahey et al., Generative adversarial network (GAN) for simulating electroencephalography, Brain Topography, 36(5) (2023) 661–670.
N. Kumari et al., Visually evoked brain signals guided image regeneration using GAN variants, Multimedia Tools and Applications, 82 (2023) 32259–32279.
M. A. Contreras-Cruz et al., Generative adversarial networks for anomaly detection in aerial images, Computers and Electrical Engineering, 106 (2023) 108470.
L. Kong et al., Multivariate time series anomaly detection with generative adversarial networks based on active distortion transformer, IEEE Sensors J., 23(9) (2023) 9658–9668.
N. Zhang, Learning adversarial transformer for symbolic music generation, IEEE Transactions on Neural Networks and Learning Systems, 34(4) (2020) 1754–1763.
Z. Shang et al., A novel small samples fault diagnosis method based on the self-attention wasserstein generative adversarial network, Neural Processing Letters, 55 (2023) 6377–6407.
S. Shao, P. Wang and R. Yan, Generative adversarial networks for data augmentation in machine fault diagnosis, Computers in Industry, 106 (2019) 85–93.
W. Hou et al., Tool wear state recognition under imbalanced data based on WGAN-GP and lightweight neural network ShuffleNet, Journal of Mechanical Science and Technology, 36(10) (2022) 4993–5009.
H. Fan et al., Intelligent data expansion approach of vibration gray texture images of rolling bearing based on improved WGAN-GP, Advances in Mechanical Engineering, 14 (3) (2022).
S. Liu et al., Data synthesis using deep feature enhanced generative adversarial networks for rolling bearing imbalanced fault diagnosis, Mechanical Systems and Signal Processing, 163 (2022) 108139.
Case Western Reserve University, Apparatus & Procedures, Case Western Reserve University, Available at: https://engineering.case.edu/bearingdatacenter/apparatus-and-procedures.
E. Bechhoefer, Condition Based Maintenance Fault Database for Testing Diagnostics and Prognostic Algorithms, MFPT.ORG, Available at: https://www.mfpt.org/fault-data-sets/ (2013).
M. Arjovsky et al., Wasserstein generative adversarial networks, Proceedings of the 34th International Conference on Machine Learning, Sydney, Austrailia (2017) 214–223.
I. Gulrajani et al., Improved training of Wasserstein GANs, arXiv:1704.00028 (2017).
A. Jolicoeur-Martineau, The relativistic discriminator: a key element missing from standard GAN, arXiv: 1807.00734 (2018).
N, Kodali et al., On convergence and stability of gans, arXiv:1705.07215 (2017).
T. Miyato et al., Spectral normalization for generative adversarial networks, arXiv:1802.05957 (2018).
A. Gretton et al., A kernel two-sample test, The J. of Machine Learning Research, 13(1) (2012) 723–773.
D. Ruan et al., Improvement of generative adversarial network and its application in bearing fault diagnosis: A review, Lubricants, 11(2) (2023) 74.
L. Wen et al., A new convolutional neural network-based data-driven fault diagnosis method, IEEE Transactions on Industrial Electronics, 65(7) (2017) 5990–5998.
L. Guo et al., Deep convolutional transfer learning network: A new method for intelligent fault diagnosis of machines with unlabeled data, IEEE Transactions on Industrial Electronics, 66(9) (2018) 7316–7325.
N. V. Chawla et al., SMOTE: synthetic minority over-sampling technique, J. of Artificial Intelligence Research, 16 (2002) 321–357.
H. He et al., ADASYN: adaptive synthetic sampling approach for imbalanced learning, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong (2008).
A. Radford, L. Metz and S. Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv:1511.06434 (2015).
C. Cortes and V. Vapnik, Support-vector networks, Machine Learning, 20 (1995) 273–297.
J. Chung et al., Empirical evaluation of gated recurrent neural networks on sequence modeling, arXiv.1412.3555 (2014).
X. Li et al., An enhanced selective ensemble deep learning method for rolling bearing fault diagnosis with beetle antennae search algorithm, Mechanical Systems and Signal Processing, 142 (2020) 106752.
Acknowledgments
The studies were funded by the National Natural Science Foundation of China (Grant numbers 61873142).
Author information
Authors and Affiliations
Corresponding author
Additional information
Jie Luo received the B.Sc. in Software Engineering from Sichuan University Jinjiang College, Sichuan, China, in 2021. Currently, he is studying for the M.E at Beijing Union University, Beijing, China. His research interests include deep learning and fault diagnosis.
Yinong Zhang received the M.E in Control Science and Engineering from Tsinghua University. Currently, she is the Vice President of the School of Urban Rail Transit and Logistics of Beijing Union University. Her main research fields are complex process modeling, intelligent control, fault diagnosis and safety evaluation.
Rights and permissions
About this article
Cite this article
Luo, J., Zhang, Y., Yang, F. et al. Imbalanced data fault diagnosis of rolling bearings using enhanced relative generative adversarial network. J Mech Sci Technol 38, 541–555 (2024). https://doi.org/10.1007/s12206-024-0104-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-024-0104-2