RESEARCH PAPER
Novel Composite Label Driven Improved GAN for High Fidelity Bearing Fault Diagnosis under Variable and Imbalanced Conditions
1
School of Electronic Engineering, Huainan Normal University, China
2
School of Information Science and Technology, Dalian Maritime University, China
3
Harbin Engineering University, China
Submission date: 2025-10-24
Final revision date: 2026-03-17
Acceptance date: 2026-03-31
Online publication date: 2026-04-25
KEYWORDS
Generative Adversarial NetworkVariable Operating ConditionsRolling Bearing Fault DiagnosisData ImbalanceComposite Label VectorAsymmetric Learning Rate
TOPICS
ABSTRACT
Rolling bearing fault diagnosis faces severe challenges from data imbalance and variable operating conditions, restricting model generalization. We propose an Improved Generative Adversarial Network (IGAN) for high-fidelity fault sample synthesis. Core innovations are: 1) A 5-dimensional Composite Label Vector (CLV) that encodes physical information (load, fault diameter, location); 2) A robust conditional injection mechanism mapping labels to a high-dimensional space for precise guidance; 3) An Asymmetric Learning Rate (ALR) strategy for training stability. Comparative experiments on the CWRU dataset demonstrate that the proposed IGAN outperforms state-of-the-art baselines, boosting classifier accuracy to 99.1%. More importantly, the model synthesizes high-fidelity data for entirely unseen operating conditions via label vector interpolation and demonstrates strong generalization on the IMS natural run-to-failure dataset. This provides a generalizable, data-driven solution for few-shot, variable-condition fault diagnosis in realistic industrial scenarios.
REFERENCES (36)
1.
Lei L, Li W, Zhang S, Wu C, Yu H. Research Progress on Data-Driven Industrial Fault Diagnosis Methods. Sensors, 2025; 25(9): 2952. doi: 10.3390/s25092952.
2.
Fan H, Xue C, Ma J, Cao X, Zhang X. A novel intelligent diagnosis method of rolling bearing and rotor composite faults based on vibration signal-to-image mapping and CNN-SVM. Measurement Science and Technology, 2023; 34(4): 044008. doi: 10.1088/1361-6501/acad90.
3.
Liu J, Zhang C, Jiang X. Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet. Mechanical Systems and Signal Processing, 2022; 168: 108664. doi: 10.1016/j.ymssp.2021.108664.
4.
Xu K, Kong X, Wang Q, Yang S, Huang N, Wang J. A bearing fault diagnosis method without fault data in new working condition combined dynamic model with deep learning. Advanced Engineering Informatics, 2022; 54: 101795. doi: 10.1016/j.aei.2022.101795.
5.
Zhang Z, Yuan X, Ye T, Zhu W, Zhou F. Bidirectional Local-Global Interaction Guided GAN with Discriminator Gradient Gap Regularization for Bearing Fault Diagnosis with Unbalanced Datasets. IEEE Sensors Journal, 2025. doi: 10.1109/JSEN.2025.3538320.
6.
Li L, Pan Z, Ma Y, Chen Z, Chen J, Wang Y. A new generative adversarial networks-based fault diagnosis framework: Learning a mapping to estimate fault. Neurocomputing, 2025; 622: 129288. doi: 10.1016/j.neucom.2024.129288.
7.
Qin Z, Zhang Z, Wu Z, Zhang Q. Fault diagnosis method for rolling bearings under a small sample dataset based on improved WGAN-GP. Measurement, 2025: 118456. doi: 10.1016/j.measurement.2025.118456.
8.
Liu Z, Zhang T, Huang Y, Mao X. Fault Diagnosis with Imbalanced Data: A Stable Sample Generation Approach Based on CWGAN-GP Model[C]//International Conference on Guidance, Navigation and Control. Singapore: Springer Nature Singapore, 2024: 582–590. doi: 10.1007/978-981-96-2228-3_54.
9.
Wang X, Jiang H, Mu M, Dong Y. A trackable multi-domain collaborative generative adversarial network for rotating machinery fault diagnosis. Mechanical Systems and Signal Processing, 2025; 224: 111950. doi: 10.1016/j.ymssp.2024.111950.
10.
Chu Z, Gu Z, Chen Y, Zhu D, Tang J. A fault diagnostic approach for underwater thrusters based on generative adversarial network. IEEE Transactions on Instrumentation and Measurement, 2024; 73: 1–14. doi: 10.1109/TIM.2024.3417591.
11.
Han X, Cao Y, Hu P, Feng W. Multi-Modal and Multi-Condition Fault Diagnosis of Rotating Machinery via a Heterogeneous Graph Learning Framework. Information Fusion, 2025: 104106. doi: 10.1016/j.inffus.2025.104106.
12.
Pham M T, Kim J M, Kim C H. Rolling bearing fault diagnosis based on improved GAN and 2-D representation of acoustic emission signals. IEEE Access, 2022; 10: 78056–78069. doi: 10.1109/ACCESS.2022.3193244.
13.
Bai G, Sun W, Cao C, Wang D, Sun Q, Sun L. GAN-based bearing fault diagnosis method for short and imbalanced vibration signal. IEEE sensors journal, 2023; 24(2): 1894–1904. doi: 10.1109/JSEN.2023.3337278.
14.
Yang J, Liu J, Xie J, Wang C, Ding T. Conditional GAN and 2-D CNN for bearing fault diagnosis with small samples. IEEE Transactions on Instrumentation and Measurement, 2021; 70: 1–12. doi: 10.1109/TIM.2021.3119135.
15.
Gao H, Zhang X, Gao X, Li F, Han H. ICoT-GAN: Integrated convolutional transformer GAN for rolling bearings fault diagnosis under limited data condition. IEEE Transactions on Instrumentation and Measurement, 2023; 72: 1–14. doi: 10.1109/TIM.2023.3271729.
16.
Jia Z, Yu B. A fault diagnosis method for rolling bearings of wind turbine generators based on MCGAN data enhancement. SN Applied Sciences, 2023; 5(10): 259. doi: 10.1007/s42452-023-05485-7.
17.
Guo C, Potekhin V V, Li P, Kovalchuk E A, Lian J. MDFT-GAN: A Multi-Domain Feature Transformer GAN for Bearing Fault Diagnosis Under Limited and Imbalanced Data Conditions. Applied Sciences, 2025; 15(11): 6225. doi: 10.3390/app15116225.
18.
Zhong H, Yu S, Trinh H, Yuan R, Lv Y, Wang Y. A time-saving fault diagnosis using simplified fast GAN and triple-type data transfer learning. Structural Health Monitoring, 2025; 24(2): 869–882. doi: 10.1177/14759217241241985.
19.
Chen H, Wei J, Huang H, Yuan Y, Wang J. Review of imbalanced fault diagnosis technology based on generative adversarial networks. Journal of Computational Design and Engineering, 2024; 11(5): 99–124. doi: 10.1093/jcde/qwae075.
20.
Wang Y, Sun G, Jin Q. Imbalanced sample fault diagnosis of rotating machinery using conditional variational auto-encoder generative adversarial network. Applied Soft Computing, 2020; 92: 106333. doi: 10.1016/j.asoc.2020.106333.
21.
Ruan D, Song X, Gühmann C, Yan J. Collaborative optimization of CNN and GAN for bearing fault diagnosis under unbalanced datasets. Lubricants, 2021; 9(10): 105. doi: 10.3390/lubricants9100105.
22.
Li W, Liu D, Li Y, Hou M, Liu J, Zhao Z, Guo A, Zhao H, Deng W. Fault diagnosis using variational autoencoder GAN and focal loss CNN under unbalanced data. Structural Health Monitoring, 2025; 24(3): 1859–1872. doi: 10.1177/14759217241254121.
23.
Yang Z, Mao R, Ye L, Liu Y, Hu X, Li Y. VSC-ACGAN: bearing fault diagnosis model applied to imbalanced samples. Measurement Science and Technology, 2025; 36(3): 036212. doi: 10.1088/1361-6501/adb872.
24.
Zhao Z, Sun S, Wang D, Xu W,. MCVAE-GAN: A novel diagnosis method for solving harmonic reducer fault signal scarcity and sample diversity problem. IEEE Transactions on Instrumentation and Measurement, 2024; 73: 1–10. doi: 10.1109/TIM.2024.3472781.
25.
Wang X, Jiang H, Wu Z, Yang Q. Adaptive variational autoencoding generative adversarial networks for rolling bearing fault diagnosis. Advanced Engineering Informatics, 2023; 56: 102027. doi: 10.1016/j.aei.2023.102027.
26.
Liu S, Jiang H, Wu Z, Li X. Data synthesis using deep feature enhanced generative adversarial networks for rolling bearing imbalanced fault diagnosis. Mechanical Systems and Signal Processing, 2022; 163: 108139. doi: 10.1016/j.ymssp.2021.108139.
27.
Luo J, Huang J, Li H. A case study of conditional deep convolutional generative adversarial networks in machine fault diagnosis. Journal of Intelligent Manufacturing, 2021;32(2): 407–425. doi: 10.1007/s10845-020-01579-w.
28.
Meng Z, Li Q, Sun D, Cao W, Fan F. An intelligent fault diagnosis method of small sample bearing based on improved auxiliary classification generative adversarial network. IEEE Sensors Journal, 2022; 22(20): 19543–19555. doi: 10.1109/JSEN.2022.3200691.
29.
Viola J, Chen Y Q, Wang J. FaultFace: Deep convolutional generative adversarial network (DCGAN) based ball-bearing failure detection method. Information Sciences, 2021; 542: 195–211. doi: 10.1016/j.ins.2020.06.060.
30.
Neupane D, Seok J. Bearing fault detection and diagnosis using case western reserve university dataset with deep learning approaches: A review. IEEE Access, 2020; 8: 93155–93178. doi: 10.1109/ACCESS.2020.2990528.
31.
Zhang C, Wei S, Dong G, Zeng Y, Zhu G, Zhou X, Liu F. Time-domain sparsity-based bearing fault diagnosis methods using pulse signal-to-noise ratio. IEEE Transactions on Instrumentation and Measurement, 2024; 73: 1–4. doi: 10.1109/TIM.2024.3375978.
32.
Zhang Q, Deng L. An intelligent fault diagnosis method of rolling bearings based on short-time Fourier transform and convolutional neural network. Journal of Failure Analysis and Prevention, 2023; 23(2): 795–811. doi: 10.1007/s11668-023-01616-9.
33.
Wang J, Han B, Bao H, Wang M, Chu Z, Shen Y. Data augment method for machine fault diagnosis using conditional generative adversarial networks. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2020; 234(12): 2719–2727. doi: 10.1177/0954407020923258.
34.
Gao X, Deng F, Yue X. Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty. Neurocomputing, 2020; 396: 487–494. doi: 10.1016/j.neucom.2018.10.109.
35.
Li Y, Song Y, Jia L, Gao S, Li Q, Qiu M. Intelligent fault diagnosis by fusing domain adversarial training and maximum mean discrepancy via ensemble learning. IEEE Transactions on Industrial Informatics, 2020; 17(4): 2833–2841. doi: 10.1109/TII.2020.3008010.
36.
Magadán L, Ruiz-Cárcel C, Granda J C, Suárez F J, Starr A. Explainable and interpretable bearing fault classification and diagnosis under limited data. Advanced Engineering Informatics, 2024; 62: 102909. doi: 10.1016/j.aei.2024.102909.
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
