Decentralized Remaining-Useful-Life Intelligence for Fleet Durability
Keywords:
Asset Health Forecasting, Edge Computing, Edge Intelligence, Fleet Resilience, Hybrid Sensor Fusion, Low-Latency Analytics, Maintenance Optimization, Predictive Maintenance, Prognostics, Risk-Informed Decision Making, Sensor Data Analytics, Structural Health Monitoring, Wind Turbine Monitoring.Abstract
We present an edge-coupled intelligence system for rapid asset health forecasting and fleet-level resilience analysis, with models informed by local, device-level edge computing. A local cluster of video, acoustic, and structural health sensors supports maintenance decision-making for a fleet of wind turbine assets, with the system designed to deliver low-latency inference, preserve the privacy of asset health data, and operate independently of cloud services.
The forecasting framework accommodates multiple prognostic modeling approaches; outputs from one such method inform asset-level risk portfolios and operational planning. A second stage schedules planned maintenance under prediction uncertainty, revealing a trade-off among downtime, cost, and future operational availability. Results show that maintenance can be scheduled with minimal future risk or cost, and that availability-informed health rules tend to favor cheaper operations at the expense of downtime. Future work will focus on calibrating assets to retain full-load availability.
References
1. Artelt, M., Weiß, M., Dittler, D., Goersch, Y., Jazdi, N., & Weyrich, M. (2024). Hybrid approaches and datasets for remaining useful life prediction: A review. Procedia CIRP, 130, 294–300.
2. Ding, G., Wang, W., & Zhao, J. (2022). Prediction of remaining useful life of rolling bearing based on fractal dimension and convolutional neural network. Measurement and Control, 55(1–2), 79–93.
3. Krishnan, M., Yandamuri, U. S., Recharla, M., Challa, K., Kolla, S. H., & Valiki, S. (2026). Adaptive Machine Learning Ecosystem for Personalized Medicine and Digital Finance: Leveraging Azure Cloud, Data Engineering, and Workflow Automation. In 2026 5th OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 5.0 (pp. 1–6). IEEE. 2026 5th OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 5.0. https://doi.org/10.1109/otcon69332.2026.11629728
4. Ding, H., Yang, L., Cheng, Z., & Yang, Z. (2021). A remaining useful life prediction method for bearing based on deep neural networks. Measurement, 172, Article 108878.
5. Ding, Y., Jia, M., Zhao, X., Yan, X., & Lee, C.-G. (2024). Joint optimization of degradation assessment and remaining useful life prediction for bearings with temporal convolutional auto-encoder. ISA Transactions, 146, 451–462.
6. Kumar, S. S., Gadi, A. L., Sheelam, G. K., Kummari, D. N., Reddy Koppolu, H. K., & Pamisetty, A. (2026). AI-Driven Compliance and Audit Framework for Manufacturing Infrastructure in Automotive Connected Services and Financial Ecosystems. In 2026 IEEE International Conference for Convergence in Computing Technology (I3CTCON) (pp. 1–6). IEEE. 2026 IEEE International Conference for Convergence in Computing Technology (I3CTCON). https://doi.org/10.1109/i3ctcon68242.2026.11507231
7. Ferreira, C., & Gonçalves, G. (2022). Remaining useful life prediction and challenges: A literature review on the use of machine learning methods. Journal of Manufacturing Systems, 63, 550–562.
8. Gao, P., Wang, J., Shi, Z., Ming, W., & Chen, M. (2024). Long-term temporal attention neural network with adaptive stage division for remaining useful life prediction of rolling bearings. Reliability Engineering & System Safety, 250, Article 110218.
9. Rajeshwari, A., Maheswari, N. U., Umamaheswari, P., Josephson, P. J., Mangalampalli, B. M., & Gudada, P. V. (2026, May). Tree-Structured Regularization Driven CNN Model for Liver Disease Diagnosis and Classification Using Ultrasound Imaging. In 2026 International Conference on Intelligent and Sustainable Electronics & Computing Technologies (INSECT) (pp. 1-6). IEEE.
10. Giannoulidis, A., & Gounaris, A. (2023). A context-aware unsupervised predictive maintenance solution for fleet management. Journal of Intelligent Information Systems, 60, 521–547.
11. Guo, J. (2023). A CNN-BiLSTM-bootstrap integrated method for remaining useful life prediction of rolling bearings. Quality and Reliability Engineering International.
12. Vincent, S. J. P., B, S., Reddy, V. A. R., Jyothi, G. B. N., Sundari, K. B. T., & Sheena, B. G. (2026). Hybrid Deep Learning Framework for Healthcare Diagnosis and Personalized Treatment Prediction. In 2026 International Conference on Emerging in Computing Technologies (INCECT) (pp. 1–6). IEEE. 2026 International Conference on Emerging in Computing Technologies (INCECT). https://doi.org/10.1109/incect72370.2026.11743003
13. He, J.-J., & Zhao, Y.-P. (2022). An improved prognostics model with its application to the remaining useful life of turbofan engine. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 236(10), 2108–2130.
14. Hu, L., He, X., & Yin, L. (2023). Remaining useful life prediction method combining the life variation laws of aero-turbofan engine and auto-expandable cascaded LSTM model. Applied Soft Computing, 145, Article 110836.
15. Subramanian, G., Premalatha, V., Peddi, R. K., Qidwai, T., Krishnamoorthi, M., & Swetha, B. (2026, August). Explainable Consumer Behavior Forecasting Using Dynamic Knowledge Graphs. In 2026 7th International Conference On Computational Vision and Bio Inspired Computing (ICCVBIC) (pp. 579-586). IEEE.
16. Ibrahim, M., Ansari, S., Ayob, A., Lipu, M. S. H., et al. (2025). Hybrid optimized remaining useful life prediction framework for lithium-ion batteries with limited data samples. Scientific Reports, 15, Article 39126.
17. Jiang, G.-J., Yang, J.-S., Cheng, T.-C., & Sun, H.-H. (2023). Remaining useful life prediction of rolling bearings based on Bayesian neural network and uncertainty quantification. Quality and Reliability Engineering International, 39(5), 1756–1774.
18. Kamat, P. V., Sugandhi, R., & Kumar, S. (2021). Deep learning-based anomaly-onset aware remaining useful life estimation of bearings. PeerJ Computer Science, 7, Article e795.
19. Gorle, R. (2023). Machine Learning-Based Access Risk Detection in Cloud Identity and Access Management Systems. Journal of International Crisis and Risk Communication Research, 241-252.
20. Kamei, S., & Taghipour, S. (2023). A comparison study of centralized and decentralized federated learning approaches utilizing the transformer architecture for estimating remaining useful life. Reliability Engineering & System Safety, 234, Article 109130.
21. Li, H., Zhang, Z., Li, T., & Si, X. (2024). A review on physics-informed data-driven remaining useful life prediction: Challenges and opportunities. Mechanical Systems and Signal Processing, 209, Article 111120.
22. Aitha, A. R., Pamisetty, V., & Recharla, M. (2026). Letter to the Editor re: “Implementation of deep learning for measurement of penile curvature on real 2D intraoperative images.” Journal of Pediatric Urology, 22(5), 106036. https://doi.org/10.1016/j.jpurol.2026.106036
23. Li, J., Zhang, M., Zheng, H., & Jie, J. (2021). Battery remaining useful life prediction using improved mutated particle filter. Energy Storage, 3, Article e218.
24. Liu, B., Gao, Z., Lu, B., Dong, H., & An, Z. (2022). Deep learning-based remaining useful life estimation of bearings with time-frequency information. Sensors, 22(19), Article 7402.
25. Mashetty, S. M. S., & Schneider, D. S. D. (2026). Continuously Delivered Lakehouse Analytics on Azure Databricks. European Journal of Advances in Artificial Intelligence, 4(03).
26. Liu, X., Chen, G., Cheng, Z., Wei, X., & Wang, H. (2022). Convolution neural network based particle filtering for remaining useful life prediction of rolling bearing. Advances in Mechanical Engineering.
27. Mu, Z., Ran, Y., Zhang, G., Wang, H., & Yang, X. (2021). Remaining useful life prediction method for machine tools based on meta-action theory. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 235(4).
28. Niazi, S. G., Huang, T., Zhou, H., Bai, S., & Huang, H.-Z. (2024). Multi-scale time series analysis using TT-ConvLSTM technique for bearing remaining useful life prediction. Mechanical Systems and Signal Processing, 206, Article 110888.
29. Pei, H., Si, X., Li, T., Zhang, Z., & Lei, Y. (2024). Interactive prognosis framework between deep learning and a stochastic process model for remaining useful life prediction. IEEE Transactions on Neural Networks and Learning Systems, 35(12), 18000–18012.
30. Peng, C., Chen, Y., Gui, W., Tang, Z., & Li, C. (2022). Remaining useful life prognosis of turbofan engines based on deep feature extraction and fusion. Scientific Reports, 12, Article 6491.
31. Mondeddula, S. R. (2025). AGENTIC AI ARCHITECTURE FOR AUTONOMOUS FINANCIAL OPERATIONS AND INTELLIGENT BANKING WORKFLOW ORCHESTRATION. International Journal of Applied Mathematics, 38(5s), 1603-1615.
32. Peng, C., Wu, J., Tang, Z., Yuan, X., & Li, C. (2022). A spatio-temporal attention mechanism based approach for remaining useful life prediction of turbofan engine. Computational Intelligence and Neuroscience, 2022, Article 9707940.
33. Reza, M. S., Mannan, M., Mansor, M., Ker, P. J., Mahlia, T. M. I., & Hannan, M. A. (2024). Recent advancement of remaining useful life prediction of lithium-ion battery in electric vehicle applications: A review of modelling mechanisms, network configurations, factors, and outstanding issues. Energy Reports, 11, 4824–4848.
34. Shetty, T. S., Gorle, R., Malani, S. R., Mattaparthi, R., & Kalra, M. (2026, August). AI-Driven Self-Healing Infrastructure Using Predictive Material Intelligence. In 2026 7th International Conference On Computational Vision and Bio Inspired Computing (ICCVBIC) (pp. 1876-1883). IEEE.
35. Samanta, A., & Williamson, S. (2023). Machine learning-based remaining useful life prediction techniques for lithium-ion battery management systems: A comprehensive review. IEEJ Journal of Industry Applications, 12(4), 563–574.
36. Shang, Y., Tang, X., Zhao, G., Jiang, P., & Lin, T. R. (2022). A remaining life prediction of rolling element bearings based on a bidirectional gated recurrent unit and convolution neural network. Measurement, 202, Article 111893.
37. Thakkar, U., & Chaoui, H. (2022). Remaining useful life prediction of an aircraft turbofan engine using deep layer recurrent neural networks. Actuators, 11(3), Article 67.
38. Gorle, R. (2024). Deep Learning Approaches for Threat Detection in Multi-Cloud Environments. Journal of Computational Analysis and Applications (JoCAAA), 33(07), 3857-3864.
39. Tong, Z., Miao, J., Tong, S., & Lu, Y. (2021). Early prediction of remaining useful life for lithium-ion batteries based on a hybrid machine learning method. Journal of Cleaner Production, 317, Article 128265.
40. Zhang, W., Jiang, N., Yang, S., & Li, X. (2025). Federated transfer learning for remaining useful life prediction in prognostics with data privacy. Measurement Science and Technology, 36, Article 076107.
Additional Files
Published
Data Availability Statement
The study uses a synthetic case study (N = 48 monitored units). The data generated and analyzed are available from the corresponding author on reasonable request.
