Remaining useful life prediction based on federated learning and cloud-edge collaboration
YU Zhenjun1,2, LEI Ningbo3, MO Yu1,2, LI Xiu2, HUANG Biqing1
1. Department of Automation, Tsinghua University, Beijing 100084, China; 2. Institute of Data and Information, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China; 3. China Nuclear Power Engineering Co., Ltd., Beijing 100840, China
Abstract：[Objective] Predicting the remaining useful life (RUL) of industrial equipment is critical for maintaining safe operations and minimizing maintenance costs. However, RUL prediction for edge devices faces several challenges. First, edge devices often lack the computational power and storage capacity required for complex RUL prediction algorithms, making such predictions difficult. Many RUL prediction algorithms require substantial resources, which are scarce on edge devices. Second, the limited data transmission rate between the cloud and edge devices causes high latency when transmitting large data sets to the cloud, affecting real-time predictions and increasing network bandwidth usage. Additionally, data sharing among all edge devices is often impractical owing to privacy, security issues, and potential conflicts of interest, limiting models to local data and reducing their accuracy.[Methods] To address these challenges, this paper proposes a cloud-edge collaboration framework for RUL prediction based on federated learning. The framework comprises two main processes. In the first process, each training device trains a variational autoencoder (VAE) using its local data set. The trained encoders are then uploaded to the cloud and aggregated using a weighted average method (FedAVG), with the number of training samples as weights. The aggregated global encoder is then downloaded to all edge devices. In the second process, the aggregated encoder extracts hidden features from the local data sets on each edge device. These features are uploaded sequentially to the cloud to train the RUL predictor. Once trained, the predictor is sent back to the edge devices, completing one training cycle. This iterative process continues until a well-trained RUL prediction model, consisting of the global encoder and predictor, is achieved. During the testing stage, the global encoder is used to extract hidden features, while the RUL predictor performs deeper feature extraction and RUL prediction. In this framework, only local encoders and hidden features are uploaded to the server, significantly reducing communication overhead. Most of the training occurs on the server, with clients only performing the basic training of the shallow VAE, thereby effectively utilizing the server's powerful computational capabilities. Data privacy is maintained since the server receives hidden features and encoders, not the original data, preventing data reconstruction.[Results] To validate the proposed method's efficiency and practicality, different network structures were tested for RUL prediction on the commercial modular aero-propulsion system simulation (C-MAPSS). Although there was a slight decline in prediction performance compared to the baseline, the difference was within acceptable limits. This minor trade-off in accuracy enabled RUL prediction under resource constraints. The proposed algorithm significantly reduced data transmission time after feature extraction across various data scales consistently. In industrial scenarios with large data volumes, this reduction was even more pronounced. Further validation using nuclear power unit fault data sets showed a slight decrease in root mean square error (RMSE) on the test set without a significant drop in prediction accuracy. These results demonstrate that the proposed cloud-edge collaboration framework is promising for fault diagnosis in nuclear power units, effectively addressing edge resource limitations. [Conclusions] The proposed cloud-edge collaboration framework leverages federated learning to achieve RUL prediction on resource-constrained edge devices, thereby alleviating issues related to resource constraints and data privacy. By employing VAE-based feature extraction and federated learning for model training, the framework achieves efficient model training while significantly reducing communication overhead with minimal impact on accuracy. Experimental validation on industrial simulation data sets and nuclear power unit fault data sets demonstrates the framework's practicality and effectiveness. This framework represents a useful approach to addressing challenges in fault diagnosis and URL prediction within resource-constrained settings.
于振军, 雷宁博, 莫语, 李秀, 黄必清. 基于联邦学习与云边协同的剩余寿命预测[J]. 清华大学学报（自然科学版）, 2025, 65(5): 901-911.
YU Zhenjun, LEI Ningbo, MO Yu, LI Xiu, HUANG Biqing. Remaining useful life prediction based on federated learning and cloud-edge collaboration. Journal of Tsinghua University(Science and Technology), 2025, 65(5): 901-911.
[1] AZADEH A, ASADZADEH S M, SALEHI N, et al. Condition-based maintenance effectiveness for series-parallel power generation system:A combined Markovian simulation model[J]. Reliability Engineering&System Safety, 2015, 142:357-368. [2] ZHAO Z Q, LIANG B, WANG X Q, et al. Remaining useful life prediction of aircraft engine based on degradation pattern learning[J]. Reliability Engineering&System Safety, 2017, 164:74-83. [3] MEDJAHER K, TOBON-MEJIA D A, ZERHOUNI N. Remaining useful life estimation of critical components with application to bearings[J]. IEEE Transactions on Reliability, 2012, 61(2):292-302. [4] NIETO P J G, GARCÍA-GONZALO E, LASHERAS F S, et al. Hybrid PSO-SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability[J]. Reliability Engineering&System Safety, 2015, 138:219-231. [5] WU D Z, JENNINGS C, TERPENNY J, et al. A comparative study on machine learning algorithms for smart manufacturing:Tool wear prediction using random forests[J]. Journal of Manufacturing Science and Engineering, 2017, 139(7):071018. [6] TOBON-MEJIA D A, MEDJAHER K, ZERHOUNI N, et al. A data-driven failure prognostics method based on mixture of Gaussians hidden Markov models[J]. IEEE Transactions on Reliability, 2012, 61(2):491-503. [7] GUCLU A, YILBOGA H, EKERÖ F, et al. Prognostics with autoregressive moving average for railway turnouts[C]//Annual Conference of the Prognostics and Health Management Society. Portland, USA, 2010. [8] LI X, DING Q, SUN J Q. Remaining useful life estimation in prognostics using deep convolution neural networks[J]. Reliability Engineering&System Safety, 2018, 172:1-11. [9] SAXENA A, GOEBEL K, SIMON D, et al. Damage propagation modeling for aircraft engine run-to-failure simulation[C]//2008 International Conference on Prognostics and Health Management. Denver, USA:IEEE, 2008:1-9. [10] XU X, WU Q H, LI X, et al. Dilated convolution neural network for remaining useful life prediction[J]. Journal of Computing and Information Science in Engineering, 2020, 20(2):021004. [11] REN L, SUN Y Q, WANG H, et al. Prediction of bearing remaining useful life with deep convolution neural network[J]. IEEE Access, 2018, 6:13041-13049. [12] HUANG C G, HUANG H Z, LI Y F, et al. A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing[J]. Journal of Manufacturing Systems, 2021, 61:757-772. [13] JIN R B, CHEN Z H, WU K Y, et al. Bi-LSTM-based two-stream network for machine remaining useful life prediction[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71:3511110. [14] ZHENG Y, BAO X Y, ZHAO F, et al. Prediction of remaining useful life using fused deep learning models:A case study of turbofan engines[J]. Journal of Computing and Information Science in Engineering, 2022, 22(5):054501. [15] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, USA:Curran Associates, 2017:6000-6010. [16] ZHANG Z Z, SONG W, LI Q Q. Dual-aspect self-attention based on transformer for remaining useful life prediction[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71:2505711. [17] MU H S, ZHAI X D, YIN D B, et al. A method of remaining useful life prediction of multi-source signals aero-engine based on RF-transformer-LSTM[C]//2022 IEEE International Conference on Systems, Man, and Cybernetics. Prague, Czech:IEEE, 2022:2502-2507. [18] QIAN Y N, YAN R Q, GAO R X. A multi-time scale approach to remaining useful life prediction in rolling bearing[J]. Mechanical Systems and Signal Processing, 2017, 83:549-567. [19] YANG Z C, WU B, SHAO J J, et al. Fault detection of high-speed train axle bearings based on a hybridized physical and data-driven temperature model[J]. Mechanical Systems and Signal Processing, 2024, 208:111037. [20] CHEN H M, QIN W, WANG L. Task partitioning and offloading in IoT cloud-edge collaborative computing framework:A survey[J]. Journal of Cloud Computing, 2022, 11(1):86. [21] LIU J L, CHEN F X, YAN J, et al. CBN-VAE:A data compression model with efficient convolutional structure for wireless sensor networks[J]. Sensors, 2019, 19(16):3445. [22] DUAN Z H, LU M, MA Z, et al. Lossy image compression with quantized hierarchical VAEs[C]//2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Waikoloa, USA:IEEE, 2023:198-207. [23] MCMAHAN B, MOORE E, RAMAGE D, et al. Communication-efficient learning of deep networks from decentralized data[C]//Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale, USA:PMLR, 2017:1273-1282. [24] WANG X D, GARG S, LIN H, et al. Toward accurate anomaly detection in industrial Internet of things using hierarchical federated learning[J]. IEEE Internet of Things Journal, 2022, 9(10):7110-7119. [25] GAO D M, WANG H Y, GUO X Z, et al. Federated learning based on CTC for heterogeneous Internet of things[J]. IEEE Internet of Things Journal, 2023, 10(24):22673-22685. [26] FICCO M, GUERRIERO A, MILITE E, et al. Federated learning for IoT devices:Enhancing TinyML with on-board training[J]. Information Fusion, 2024, 104:102189. [27] HAN X, YU H R, GU H S. Visual inspection with federated learning[C]//16th International Conference on Image Analysis and Recognition. Waterloo, Canada:Springer, 2019:52-64. [28] LUAN Z R, LAI Y J, XU Z C, et al. Federated learning-based insulator fault detection for data privacy preserving[J]. Sensors, 2023, 23(12):5624. [29] ZEILER M D, KRISHNAN D, TAYLOR G W, et al. Deconvolutional networks[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA:IEEE, 2010:2528-2535. [30] WU Q H, DING K Q, HUANG B Q. Approach for fault prognosis using recurrent neural network[J]. Journal of Intelligent Manufacturing, 2020, 31(7):1621-1633. [31] HEIMES F O. Recurrent neural networks for remaining useful life estimation[C]//2008 International Conference on Prognostics and Health Management. Denver, USA:IEEE, 2008:1-6. [32] MO Y, WU Q H, LI X, et al. Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit[J]. Journal of Intelligent Manufacturing, 2021, 32(7):1997-2006. [33] BABU G S, ZHAO P L, LI X L. Deep convolutional neural network based regression approach for estimation of remaining useful life[C]//21st International Conference on Database Systems for Advanced Applications. Dallas, USA:Springer, 2016:214-228. [34] ZHENG S, RISTOVSKI K, FARAHAT A, et al. Long short-term memory network for remaining useful life estimation[C]//2017 IEEE International Conference on Prognostics and Health Management. Dallas, USA:IEEE, 2017:88-95.
2025, Vol. 65 
