Flexible Federated Learning in Machinery Fault Diagnostics With Light Communication

Xiang Li; Weipeng Fan; Shaojie Yang; Wei Zhang; Xu Li

doi:10.1109/JAS.2025.125414

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 19.2, Top 1 (SCI Q1)

CiteScore: 28.2, Top 1% (Q1)
Google Scholar h5-index: 95， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2026 > In Press, Accepted Manuscript

X. Li, W. Fan, S. Yang, W. Zhang, and X. Li, “Flexible federated learning in machinery fault diagnostics with light communication,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 3, pp. 1–12, Mar. 2026. doi: 10.1109/JAS.2025.125414

Citation:

X. Li, W. Fan, S. Yang, W. Zhang, and X. Li, “Flexible federated learning in machinery fault diagnostics with light communication,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 3, pp. 1–12, Mar. 2026. doi: 10.1109/JAS.2025.125414

Citation:

PDF( 0 KB)

Flexible Federated Learning in Machinery Fault Diagnostics With Light Communication

doi: 10.1109/JAS.2025.125414

Funds: This work was supported by the National Natural Science Foundation of China (52475125), the Aviation Science Foundation (2024Z071070001), and Education Ministry of China (HZKY20220429)

More Information

Author Bio:
Xiang Li (Senior Member, IEEE) received the B.S. degree in engineering mechanics and the Ph.D. degree in mechanics from Tianjin University, in 2012 and 2017, respectively. He is currently a Professor with School of Mechanical Engineering, Xi’an Jiaotong University. Prior to joining Xi’an Jiaotong University, he was a Postdoctoral Fellow in the Center for Intelligent Maintenance Systems at the University of Cincinnati, US. His research interests include industrial AI, machine vision, neuromorphic computing, and large multimodal model. He is an IET Fellow. He serves as the Associate Editors for IEEE Transactions on Neural Networks and Learning Systems, Expert Systems With Applications, and Pattern Recognition. He is selected as the Highly Cited Researcher by Clarivate

Weipeng Fan received the B.S. degree in electrical engineering and automation from Lanzhou University of Technology in 2020 and the M.S. degree in detection technology and automatic equipment from Yanshan University in 2023. He is currently pursuing the Ph.D. degree in mechanical engineering at the Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University. His research interests include machinery condition monitoring and fault diagnosis, structural health monitoring, and neuromorphic computing and its applications on time series data

Shaojie Yang received the B.S. degree in biomedical engineering in 2017 and the M.S. degree in Mechanical Engineering in 2020, both from the University of Cincinnati, Cincinnati, USA. He is currently pursuing the Ph.D. degree in the Department of Mechanical and Aerospace Engineering at the University of California, San Diego, USA. His research interests include health prognostics and fault diagnostics, state estimation and prediction, and machine vision for lithium-ion batteries

Wei Zhang received the Ph.D. degree in mechanics from Tianjin University in 2017. She was a Visiting Scholar with Texas A & M University, USA in 2015. She is currently a Professor with the School of Aerospace Engineering, Shenyang Aerospace University. She is selected as the Highly Cited Researcher by Clarivate, and the Emerging Leader by Measurement Science and Technology. She is on the editorial boards of Measurement, Journal of Dynamics, Monitoring and Diagnostics, etc. Her research interests include rotor dynamics, fault diagnosis, industrial AI, and battery health management

Xu Li received the Ph.D. degree in material processing engineering from Northeastern University in 2009. He is currently a Full Professor with the State Key Laboratory of Rolling and Automation, Northeastern University. His research interests include rolling process, fault diagnosis, automation systems, and intelligent control
Corresponding author: Wei Zhang, e-mail: 1012201003@tju.edu.cn
Received Date: 2024-05-03
Accepted Date: 2025-03-06

Available Online: 2026-02-13

Abstract

Abstract

While data-driven fault diagnosis methods have been successfully developed in the past years, large amounts of high-quality condition monitoring data are generally required to ensure model performance. Due to the high economic and labor costs in data collection, it is difficult for a single user to build an effective database, and exploring data of multiple users for better training becomes a promising solution. However, data privacy is of great importance in the real industries due to conflicts of interests, and direct data aggregation from different users is hardly feasible. To address this issue, a flexible federated learning method is proposed in this paper. Different from most existing methods with identical models under the federation, different customized individual deep neural network models can be used at different clients. Public data are exploited for knowledge transfer. Only the scores on public data are communicated between clients and server, rather than the whole model parameters. That significantly reduces the communication and computational burden. Experiments are carried out on two real-world machinery fault diagnosis datasets, and the results show the proposed method is promising for data privacy-preserving federated learning with flexible models and light communications.
- Collaborative modeling,
- data privacy,
- deep learning,
- fault diagnosis,
- federated learning

FullText(HTML)

References(43)

References

[1]	J. Huang, Z. Li, and Z. Zhou, “A simple framework to generalized zero-shot learning for fault diagnosis of industrial processes,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 6, pp. 1504−1506, 2023. doi: 10.1109/JAS.2023.123426
[2]	C. Yang, K. Zhou, and J. Liu, “Supergraph: Spatial-temporal graphbased feature extraction for rotating machinery diagnosis,” IEEE Trans. Industrial Electronics, vol. 69, no. 4, pp. 4167–4176, 2022. doi: 10.1109/TIE.2021.3075871
[3]	X. Li, Y. Xu, N. Li, B. Yang, and Y. Lei, “Remaining useful life prediction with partial sensor malfunctions using deep adversarial networks,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 1, pp. 121–134, 2023. doi: 10.1109/JAS.2022.105935
[4]	H. Zhao, J. Liu, H. Chen, J. Chen, Y. Li, J. Xu, and W. Deng, “Intelligent diagnosis using continuous wavelet transform and gauss convolutional deep belief network,” IEEE Trans. Reliability, pp. 1–11, 2022.
[5]	C. Tang, B. Yang, X. Xie, G. Chen, M. A. A. Al-qaness, and Y. Liu, “An incentive mechanism for federated learning: A continuous zero-determinant strategy approach,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 1, p. 88–102, 2024. doi: 10.1109/JAS.2023.124182
[6]	A. Chaddad, Q. Lu, J. Li, Y. Katib, R. Kateb, C. Tanougast, A. Bouridane, and A. Abdulkadir, “Explainable, domain-adaptive, and federated artificial intelligence in medicine,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 4, p. 859–876, 2023. doi: 10.1109/JAS.2023.123123
[7]	W. Huang, M. Ye, Z. Shi, and B. Du, “Generalizable heterogeneous federated cross-correlation and instance similarity learning,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 46, no. 2, pp. 712–728, 2024. doi: 10.1109/TPAMI.2023.3327373
[8]	R. Zhao, L. T. Yang, D. Liu, and W. Lu, “Tensor-enabled communication-efficient and trustworthy federated learning for heterogeneous intelligent space-air-ground-integrated IoT,” IEEE Internet of Things J., vol. 10, no. 23, pp. 20285–20296, 2023. doi: 10.1109/JIOT.2023.3283853
[9]	K. I. K. Wang, X. Zhou, W. Liang, Z. Yan, and J. She, “Federated transfer learning based cross-domain prediction for smart manufacturing,” IEEE Trans. Industrial Informatics, vol. 18, no. 6, pp. 4088–4096, 2022. doi: 10.1109/TII.2021.3088057
[10]	X. Li, H. Shao, S. Lu, J. Xiang, and B. Cai, “Highly efficient fault diagnosis of rotating machinery under time-varying speeds using LSISMM and small infrared thermal images,” IEEE Trans. Systems, Man, and Cybernetics: Systems, vol. 52, no. 12, pp. 7328–7340, 2022. doi: 10.1109/TSMC.2022.3151185
[11]	R. Chen, L. Li, K. Xue, C. Zhang, M. Pan, and Y. Fang, “Energy efficient federated learning over heterogeneous mobile devices via joint design of weight quantization and wireless transmission,” IEEE Trans. Mobile Computing, vol. 22, no. 12, pp. 7451–7465, 2023.
[12]	Y. Wu, J. Song, X. Wu, X. Wang, and S. Lu, “Fault diagnosis of linear guide rails based on SSTG combined with CA-DenseNet,” J. Dynamics, Monitoring and Diagnostics, vol. 3, no. 1, pp. 1–10, 2024.
[13]	X. Li, W. Zhang, X. Li, and H. Hao, “Partial domain adaptation in remaining useful life prediction with incomplete target data,” IEEE/ASME Trans. Mechatronics, pp. 1–11, 2023.
[14]	J. He, M. Ouyang, Z. Chen, D. Chen, and S. Liu, “A deep transfer learning fault diagnosis method based on WGAN and minimum singular value for non-homologous bearing,” IEEE Trans. Instrumentation and Measurement, vol. 71, pp. 1–9, 2022.
[15]	W. Li, R. Huang, J. Li, Y. Liao, Z. Chen, G. He, R. Yan, and K. Gryllias, “A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: Theories, applications and challenges,” Mechanical Systems and Signal Processing, vol. 167, p. 108487, 2022. doi: 10.1016/j.ymssp.2021.108487
[16]	B. Yang, S. Xu, Y. Lei, C.-G. Lee, E. Stewart, and C. Roberts, “Multisource transfer learning network to complement knowledge for intelligent diagnosis of machines with unseen faults,” Mechanical Systems and Signal Processing, vol. 162, p. 108095, 2022. doi: 10.1016/j.ymssp.2021.108095
[17]	J. Liu, C. Zhang, and X. Jiang, “Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet,” Mechanical Systems and Signal Processing, vol. 168, p. 108664, 2022. doi: 10.1016/j.ymssp.2021.108664
[18]	H. Liu, J. Zhou, Y. Zheng, W. Jiang, and Y. Zhang, “Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders,” ISA Trans., vol. 77, pp. 167–178, 2018. doi: 10.1016/j.isatra.2018.04.005
[19]	Y. Wu, M. Yuan, S. Dong, L. Lin, and Y. Liu, “Remaining useful life estimation of engineered systems using vanilla LSTM neural networks,” Neurocomputing, vol. 275, pp. 167–179, 2018. doi: 10.1016/j.neucom.2017.05.063
[20]	K. M. Almutairi and J. K. Sinha, “A comprehensive 3-steps methodology for vibration-based fault detection, diagnosis and localization in rotating machines,” J. Dynamics, Monitoring and Diagnostics, vol. 3, no. 1, pp. 49–58, 2024.
[21]	Z. Ye, X. Zhang, X. Chen, H. Xiong, and D. Yu, “Adaptive clustering based personalized federated learning framework for next POI recommendation with location noise,” IEEE Trans. Knowledge and Data Engineering, pp. 1–14, 2023.
[22]	W. Zhang and X. Li, “Data privacy preserving federated transfer learning in machinery fault diagnostics using prior distributions,” Structural Health Monitoring, vol. 21, no. 4, pp. 1329–1344, 2021.
[23]	Y. Cheng, J. Lu, D. Niyato, B. Lyu, J. Kang, and S. Zhu, “Federated transfer learning with client selection for intrusion detection in mobile edge computing,” IEEE Communications Letters, vol. 26, no. 3, pp. 552–556, 2022. doi: 10.1109/LCOMM.2022.3140273
[24]	Y. Li, W. Zhou, H. Mi, Y. Wang, and H. Wang, “FedH2L: A federated learning approach with model and statistical heterogeneity,” in Proc. IEEE Int. Conf. Joint Cloud Computing, pp. 25–33, 2023.
[25]	Y. H. Chan and E. C. H. Ngai, “FedHe: Heterogeneous models and communication-efficient federated learning,” in Proc. 17th Int. Conf. Mobility, Sensing and Networking, pp. 207–214, 2021.
[26]	B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. Y. Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Proc. the 20th Int. Conf. Artificial Intelligence and Statistics, vol. 54, pp. 1273–1282, 2017.
[27]	A. Hard, K. Rao, R. Mathews, S. Ramaswamy, F. Beaufays, S. Augenstein, H. Eichner, C. Kiddon, and D. Ramage, “Federated learning for mobile keyboard prediction,” arXiv Preprint arXiv: 1811.03604, 2018.
[28]	Y. M. Saputra, D. T. Hoang, D. N. Nguyen, E. Dutkiewicz, M. D. Mueck, and S. Srikanteswara, “Energy demand prediction with federated learning for electric vehicle networks,” in Proc. IEEE Global Communications Conf., pp. 1–6, 2019.
[29]	W. Zhang, X. Li, H. Ma, Z. Luo, and X. Li, “Federated learning for machinery fault diagnosis with dynamic validation and self-supervision,” Knowledge-Based Systems, vol. 213, p. 106679, 2021. doi: 10.1016/j.knosys.2020.106679
[30]	X. Li, C. Zhang, X. Li, and W. Zhang, “Federated transfer learning in fault diagnosis under data privacy with target self-adaptation,” J. Manufacturing Systems, vol. 68, pp. 523–535, 2023. doi: 10.1016/j.jmsy.2023.05.006
[31]	D. Li and J. Wang, “FedMD: Heterogenous federated learning via model distillation,” arXiv preprint arXiv: 1910.03581, 2019.
[32]	P. Qi, X. Zhou, Y. Ding, Z. Zhang, S. Zheng, and Z. Li, “FedBKD: Heterogenous federated learning via bidirectional knowledge distillation for modulation classification in IoT-Edge system,” IEEE J. Selected Topics in Signal Processing, vol. 17, no. 1, pp. 189–204, 2023. doi: 10.1109/JSTSP.2022.3224597
[33]	Y. Hu, X. Sun, Y. Tian, L. Song, and K. C. Tan, “Communication efficient federated learning with heterogeneous structured client models,” IEEE Trans. Emerging Topics in Computational Intelligence, vol. 7, no. 3, pp. 753–767, 2023.
[34]	W. Lu, B. Liang, Y. Cheng, D. Meng, J. Yang, and T. Zhang, “Deep model based domain adaptation for fault diagnosis,” IEEE Trans. Industrial Electronics, vol. 64, no. 3, pp. 2296–2305, 2017. doi: 10.1109/TIE.2016.2627020
[35]	Z. Zhang, C. Guan, H. Chen, X. Yang, W. Gong, and A. Yang, “Adaptive privacy-preserving federated learning for fault diagnosis in internet of ships,” IEEE Internet of Things J., vol. 9, no. 9, pp. 6844–6854, 2022. doi: 10.1109/JIOT.2021.3115817
[36]	W. Zhang, Z. Wang, and X. Li, “Blockchain-based decentralized federated transfer learning methodology for collaborative machinery fault diagnosis,” Reliability Engineering and System Safety, p. 108885, 2022.
[37]	X. Peng, Z. Huang, Y. Zhu, and K. Saenko, “Federated adversarial domain adaptation,” in Proc. Int. Conf. Learning Representations, 2019.
[38]	A. Gretton, K. Borgwardt, M. Rasch, B. Schölkopf, and A. Smola, “A kernel two-sample test,” J. Machine Learning Research, vol. 13, pp. 723–773, 2012.
[39]	H. Li, S. J. Pan, S. Wang, and A. C. Kot, “Domain generalization with adversarial feature learning,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 5400–5409, 2018.
[40]	Y. Li, K. Swersky, and R. Zemel, “Generative moment matching networks,” in Proc. 32nd Int. Conf. Machine Learning, pp. 1718–1727, 2015.
[41]	A. Gretton, D. Sejdinovic, H. Strathmann, S. Balakrishnan, M. Pontil, K. Fukumizu, and B. K. Sriperumbudur, Optimal kernel choice for largescale two-sample tests. Curran Associates, Inc., 2012.
[42]	W. A. Smith and R. B. Randall, “Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study,” Mechanical Systems and Signal Processing, vol. 64-65, pp. 100–131, 2015. doi: 10.1016/j.ymssp.2015.04.021
[43]	W. Zhang and X. Li, “Federated transfer learning for intelligent fault diagnostics using deep adversarial networks with data privacy,” IEEE/ASME Trans. Mechatronics, vol. 27, no. 1, pp. 430–439, 2022. doi: 10.1109/TMECH.2021.3065522

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(7) / Tables(5)

Get Citation

PDF

XML

Article Metrics

Article views (16) PDF downloads(0)

Flexible Federated Learning in Machinery Fault Diagnostics With Light Communication

doi: 10.1109/JAS.2025.125414

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Export File

Citation

Format

Content