Hierarchical Multi-Scale Entropy and Deep Learning for Incipient Bearing Fault Diagnosis
Keywords:
Hierarchical Multi-Scale Entropy, Deep Learning, Bearing Fault Diagnosis, Incipient Faults, Predictive MaintenanceAbstract
The reliable operation of rotating machinery is highly dependent on the health of rolling element bearings, which are ubiquitous components in modern industrial applications. The detection of incipient faults in these bearings is a critical challenge due to the weak signature of early-stage degradation, which is often masked by heavy background noise and complex structural vibrations. This paper presents a novel framework for incipient bearing fault diagnosis that integrates Hierarchical Multi-Scale Entropy with advanced deep learning architectures. By employing a hierarchical decomposition strategy, the proposed method successfully captures dynamic complexity across both low and high-frequency scales, overcoming the limitations of traditional multi-scale entropy methods that predominantly focus on lower frequencies. The extracted entropy features, which represent the nonlinear dynamic characteristics of the vibration signals, are subsequently fed into a custom-designed convolutional neural network for automated feature abstraction and classification. Through extensive theoretical analysis and experimental validation on established benchmark datasets, the proposed hybrid approach demonstrates superior diagnostic accuracy, robustness to varying noise conditions, and enhanced sensitivity to localized microscopic defects compared to existing methodologies. The results confirm that the synergy between advanced nonlinear dynamics analysis and deep learning offers a highly effective solution for predictive maintenance, thereby reducing unexpected downtime and operational costs in industrial environments
References
1. Cao, L., Huang, X., Ye, H., & Song, Y. (2023). Neuroadaptive asymptotic tracking control with guaranteed performance under mismatched uncertainties and saturated inputs. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 53(6), 3784-3794.
2. Zhang, S., Yang, S., Zhang, W., Xiong, Y., & Yao, S. (2026). Hybrid Beamforming for Subarray-Level Movable Antenna Enhanced MU-MIMO Communications. IEEE Wireless Communications Letters, 15, 2559-2563.
3. Li, K., Ren, Y., Fan, D., Liu, L., Wang, Z., & Ma, Z. (2018). Enhance GO methodology for reliability analysis of the closed-loop system using Cyclic Bayesian Networks. Mechanical Systems and Signal Processing, 113, 237-252.
4. Ke, Z., Zhou, S., Zhou, Y., Chang, C. H., & Zhang, R. (2025, March). Detection of ai deepfake and fraud in online payments using gan-based models. In 2025 8th International Conference on Advanced Algorithms and Control Engineering (ICAACE) (pp. 1786-1790). IEEE.
5. Lv, Qi, et al. "Spatial-temporal graph diffusion policy with kinematic modeling for bimanual robotic manipulation." Proceedings of the Computer Vision and Pattern Recognition Conference. 2025.
6. Xu, Haoyan, et al. "Graph synthetic out-of-distribution exposure with large language models." arXiv preprint arXiv:2504.21198 (2025).
7. Pan, J., Lu, B., Gu, D., Xia, Z., & Xia, T. (2015). Mechanical behavior of rectangular steel-reinforced ECC/concrete composite column under eccentric compression. Transactions of Tianjin University, 21(3), 269-277.
8. Zhang, S., & Yan, W. (2025). In-trainNet: A Two-Step Data-Driven Framework for Enhancing Railway In-Train Forces Monitoring. Advanced Engineering Informatics, 65, 103352.
9. Fan, D., Liu, M., Hai, X., Ren, Y., & Feng, Q. (2024). Higher-order rewiring strategy for enhancing robustness of multiplex aviation networks. IEEE transactions on network science and engineering, 11(6), 6417-6430.
10. Fan, D., Lin, J., Cai, B., & Liu, B. (2021). Robustness of maintenance support service networks: Attributes, evaluation and improvement. Reliability Engineering & System Safety, 210, 107526.
11. DeCandia, G., Hastorun, D., Jampani, M., Kakulapati, G., Lakshman, A., Pilchin, A., et al. (2007). Dynamo: Amazon’s highly available key-value store. In Proceedings of SOSP.
12. Gu, D., Sun, Y., Hu, J., Lu, R., & Pan, J. (2026). Rheology-and fracture-guided design of lightweight spray-applied engineered cementitious composites achieving structural-grade strength and high tensile ductility. Journal of Building Engineering, 116100.
13. Xing, J., & Xu, J. (2022). An improved convolutional neural network for recognition of incipient faults. IEEE Sensors Journal, 22(16), 16314-16322.
14. Zhang, C., & Zhao, Y. (2017). High precision deep sea geomagnetic data sampling and recovery with three-dimensional compressive sensing. IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences, 100(9), 1760-1762.
15. Burrows, M. (2006). The Chubby lock service for loosely-coupled distributed systems. In Proceedings of OSDI.
16. Ren, Y., Fan, D., Wang, Z., Yang, D., Feng, Q., Sun, B., & Liu, L. (2018). System dynamic behavior modeling based on extended GO methodology. IEEE Access, 6, 22513-22523.
17. Liu, L., Fan, D., Wang, Z., Yang, D., Cui, J., Ma, X., & Ren, Y. (2019). Enhanced GO methodology to support failure mode, effects and criticality analysis. Journal of Intelligent Manufacturing, 30(3), 1451-1468.
18. Lijun, X., Yehui, Z., Yue, S., Fanglei, Z., Honghua, J., & Guangming, W. (2022). Research on the current situation of continuously variable transmission and electric drive technology. Journal of Chinese Agricultural Mechanization, 43(7), 81.
19. Zhang, W. (2026). A 5-6 GHz PVT Robust Current Mode Passive Mixer for Direct Down-Conversion Receiver.
20. Gu, D., Jiang, B., Lin, J., Xu, L., & Pan, J. (2025). Shear behaviour of steel-headed stud connectors in engineered cementitious composite (ECC) bridge deck under positive and negative moments. Engineering Structures, 324, 119316.
21. Li, C., Xu, J., & Xing, J. (2023). A frequency feature extraction method based on convolutional neural network for recognition of incipient fault. IEEE Sensors Journal, 24(1), 564-572.
22. Yao, Y., Zhang, W., & Li, M. (2026). Cloud-Edge Federated Incremental Learning Framework for PMSM Efficiency Optimization with Lightweight CNN-LSTM Models and OTA Differential Deployment. Journal of Computer Science and Frontier Technologies, 3(1), 98-111.
23. Zhang, W., Luo, M., & Chen, Z. (2024, October). Hybrid Forecasting: ML Predictions of Lake-Effect Regional Extreme Precipitations. In 2024 7th International Conference on Universal Village (UV) (pp. 1-11). IEEE.
24. Zaharia, M., Chowdhury, M., Franklin, M. J., Shenker, S., & Stoica, I. (2012). Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In Proceedings of NSDI.
25. Zhang, C., Jiang, X., & Zhao, Y. (2021). Efficient instantaneous channel propagation modeling for aeronautical communications systems with compressed sensing. IEEE Transactions on Antennas and Propagation, 70(2), 1211-1220.
26. Fan, J., Liang, W., & Zhang, W. Q. (2025). SARNet: A Spike-Aware consecutive validation Framework for Accurate Remaining Useful Life Prediction. arXiv preprint arXiv:2510.22955.
27. Xing, J., & Xu, J. (2022). An improved incipient fault diagnosis method of bearing damage based on hierarchical multi-scale reverse dispersion entropy. Entropy, 24(6), 770.
28. Bao, Zerui, et al. "SLOFetch: Compressed-Hierarchical Instruction Prefetching for Cloud Microservices." arXiv preprint arXiv:2511.04774 (2025).
29. Zaharia, M., Chowdhury, M., Das, T., Dave, A., Ma, J., McCauley, M., et al. (2010). Spark: Cluster computing with working sets. In Proceedings of HotCloud.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Adlai Arthur, Daiki Yamamoto, Quentin Renaud
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in this journal are licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
