Research Review on Federated Learning Technology for Fault Diagnosis
Main Article Content
Keywords
federated learning, fault diagnosis, non-IID, privacy protection, lightweight model
Abstract
Federated learning (FL) is a distributed machine learning (ML) method. This technology only needs to exchange model parameters without sharing private data and plays an important role in industrial fault diagnosis. This paper focuses on analysing four mainstream technical schemes: fault diagnosis methods based on traditional federated learning, fault diagnosis methods based on federated deep learning, optimized federated fault diagnosis methods for nonindependent and identically distributed (non-IID) data, and lightweight federated fault diagnosis methods for edge device deployment. This paper systematically sorts out the federated learning technologies for fault diagnosis, summarizes the practical challenges existing in these technical schemes, and proposes corresponding future research prospects, providing specific references for the innovation and implementation of federated learning technologies for fault diagnosis.
References
- [1] Wang, X., Huang, Q. C., & Sun, L. Y. (2025). A Review of Personalized Federated Learning. Journal of Chinese Computer Systems, 1-13. https://doi.org/10.20009/j.cnki.21-1106/TP.2025-0399.
- [2] Zhang, S. Q., Wang, H. F., Wang, Z. P., Zhao, P., Liu, Y. H., Chi, Z. H., & Zhao, X. S. (2025). A Review of Federated Learning-Driven Network Intrusion Detection. Computer Engineering and Applications, 1-19.
- [3] Feng, W. J., Yang, Y. Q., Jia, Z. H., & Zhang, L. L. (2025). Optimization Methods of Federated Learning Under Non-Independent and Identically Distributed and Long-Tailed Distributions. Journal of Xinjiang University (Natural Science Edition in Chinese and English), 42(04), 425-433. https://doi.org/10.13568/j.cnki.651094.651316.2024.12.30.0001.
- [4] Fu, P. F., Sun, A., Yao, K. M., Li, H. J., & Ma, J. L. J. (2025). A Small-Sample Bearing Fault Diagnosis Method Based on STFT-SWT-2DCNN-SVM. In Proceedings of the 36th Chinese Process Control Conference (Volume 2) (pp. 1028-1035). School of Automation and Information Engineering, Sichuan University of Science & Engineering; Sichuan Provincial Key Laboratory of Artificial Intelligence.
- [5] Li, H. (2025). Research on Bearing Fault Diagnosis Based on Federated Learning (Master's Thesis). Shijiazhuang Tiedao University. https://doi.org/10.27334/d.cnki.gstdy.2025.000599.
- [6] Wang, R. L., Yan, K., Ning, Z. J., & Xiao, X. (2025). Federated Learning-Based Industrial Instrument Localization and Classification Algorithm for Non-IID Data. Instrument Technique and Sensor, (11), 19-24.
- [7] Wang, S. X., Cao, Z., Zhao, Q. Y., Feng, X. C., & Rong, C. Y. (2026). A Lightweight Load Decomposition Method Based on Federated Learning and Knowledge Distillation. Journal of Tianjin University (Science and Technology), 59(01), 52-64.
- [8] Sun, H. B., Wang, G. C., Zhang, L., Wang, Y., & Guo, Y. A. (2025). Adaptive Selection Strategy of Federated Learning Clients Based on Deep Reinforcement Learning. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 1-13.
- [9] Fu, H. Y. (2024). Research on Lightweight Federated Learning Technology for Edge-Side Object Recognition (Master's Thesis). Beijing University of Posts and Telecommunications. https://doi.org/10.26969/d.cnki.gbydu.2024.001699.
- [10] Cao, Y. F., Luo, Q. R., & Zhang, L. (2025). Data Mixing Poisoning Attack Based on Federated Learning. Computer Engineering, 1-8. https://doi.org/10.19678/j.issn.1000-3428.0252414.
- [11] Shi, X. J., Zhu, X. L., & Xiao, W. T. (2026). FedReg*: Addressing the Challenges in Non-Independent and Identically Distributed Scenarios for Federated Learning (in English). Journal of Donghua University (English Edition), 43(01), 41-49. https://doi.org/10.19884/j.1672-5220.202412011.
- [12] Hou, J. K., Guo, R., Zhang, Y. H., & Liu, G. J. (2025). A Personalized Federated Learning Scheme with Differential Privacy for Heterogeneous Data. Application Research of Computers, 1-13. https://doi.org/10.19734/j.issn.1001-3695.2025.09.0411.
- [13] Yu, C. Y., Lian, G. Q., & Su, W. (2026). A Review of Key Technologies of Federated Learning in Non-Independent and Identically Distributed Ultra-High Dimensional Scenarios. Information Technology and Standardization, (Z1), 50-56+62.
- [14] Wang, J., Peng, Y. J., Zhang, Z. J., Tian, J., Zhu, J. M., & Li, H. T. (2025). A Personalized Differential Privacy Federated Learning Method Based on Knowledge Distillation. Journal of Xidian University, 1-18. https://doi.org/10.19665/j.issn1001-2400.20260108.
- [15] Guo, J. L., Chen, Y. Q., Lu, R., & Li, G. C. (2025). A Privacy-Preserving Decentralized Recommendation System Based on Blockchain and Federated Learning. Application Research of Computers, 1-10. https://doi.org/10.19734/j.issn.1001-3695.2025.09.0301.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.