A Cyber Physical Framework for Intelligent Fault Detection and Predictive Maintenance in Digital Power Grids
DOI:
https://doi.org/10.4108/ew.13931Keywords:
Cyber–Physical Power Systems, Fault Detection, GRU, Fault Localization, Predictive MaintenanceAbstract
INTRODUCTION: The increasing complexity of modern digital power grids demands intelligent and reliable fault detection and predictive maintenance solutions to ensure operational stability, resilience, and efficient asset management. Integrating cyber–physical systems with advanced deep learning techniques enables accurate monitoring and proactive maintenance of power transmission networks.
OBJECTIVES: This study proposes a unified GRU-based cyber–physical framework for intelligent fault detection, fault classification, fault localization, and risk-based predictive maintenance in power transmission systems, while improving diagnostic accuracy, interpretability, and maintenance decision-making.
METHODS: The proposed framework integrates multi-parametric voltage and current measurements from the physical layer with a gated recurrent unit (GRU) model in the cyber layer to capture the temporal dynamics of fault evolution. Domain-informed electrical features, including voltage deviation, phase imbalance index, and current severity index, are incorporated to improve physical interpretability. A multi-task learning strategy is employed to simultaneously detect faults, classify fault types, identify faulted transmission lines, estimate fault locations, and generate a risk-based maintenance index for proactive maintenance prioritization.
RESULTS: The proposed framework achieved a fault classification accuracy of 98.61%, with precision of 0.9864, recall of 0.9861, and F1-score of 0.9861. Fault localization was performed with a low mean absolute error (MAE) of 0.0303, demonstrating high localization accuracy. The risk-based maintenance index effectively supported proactive maintenance prioritization for transmission assets.
CONCLUSION: The proposed GRU-based cyber–physical framework provides an effective and scalable solution for intelligent power grid monitoring by integrating accurate fault detection, precise fault localization, and predictive maintenance within a unified architecture. The framework enhances operational reliability and supports data-driven maintenance strategies for next-generation digital power grids.
Downloads
References
[1] Heiden PZ, Priefer J, Beverungen D. Predictive maintenance on the energy distribution grid–design and evaluation of a digital industrial platform in the context of a smart service system. IEEE Trans Eng Manag. 2024;71:3641-3655. doi:10.1109/TEM.2024.3352819.
[2] Ali M, Kaddoum G, Li WT, Yuen C, Tariq M, Poor HV. A smart digital twin enabled security framework for vehicle-to- grid cyber-physical systems. IEEE Trans Inf Forensics Secur. 2023;18:5258-5271. doi:10.1109/TIFS.2023.3305916.
[3] Mirshekali H, Santos AQ, Shaker HR. A survey of time- series prediction for digitally enabled maintenance of electrical grids. Energies. 2023;16(17):6332. doi:10.3390/en16176332.
[4] Chae J, Lee S, Jang J, Hong S, Park KJ. A survey and perspective on industrial cyber-physical systems (ICPS): from ICPS to AI-augmented ICPS. Trans Ind Cyber-Phys Syst. 2023;1:257-272. doi:10.1109/TICPS.2023.3323600.
[5] Ricciardi Celsi L, Valli A. Applied control and artificial intelligence for energy management: an overview of trends in EV charging, cyber-physical security and predictive maintenance. Energies. 2023;16(12):4678. doi:10.3390/en16124678.
[6] Khan S, Mazhar T, Shahzad T, Khan MA, Rehman AU, Hamam H. Integration of smart grid with Industry 5.0: applications, challenges and solutions. Measurement: Energy. 2025;5:100031. doi:10.1016/j.meaene.2024.100031.
[7] Singh RR, Bhatti G, Kalel D, Vairavasundaram I, Alsaif F. Building a digital twin powered intelligent predictive maintenance system for industrial AC machines. Machines. 2023;11(8):796. doi:10.3390/machines11080796.
[8] Omiyale BO, Ogedengbe II, Odeyemi J, Ogbeyemi A, Olorunsogbon F, Zhang WC. Mitigating 3D printing defects via cyber-physical systems: a process for fabricating defect- free components. Int J Adv Manuf Technol. 2025;139(7- 8):3175-3196. doi:10.1007/s00170-025-16100-x.
[9] Molęda M, Małysiak-Mrozek B, Ding W, Sunderam V, Mrozek D. From corrective to predictive maintenance—a review of maintenance approaches for the power industry. Sensors. 2023;23(13):5970. doi:10.3390/s23135970.
[10] Musa AA, Hussaini A, Liao W, Liang F, Yu W. Deep neural networks for spatial-temporal cyber-physical systems: a survey. Future Internet. 2023;15(6):199. doi:10.3390/fi15060199.
[11] Manias DM, et al. Trends in smart grid cyber-physical security: components, threats, and solutions. IEEE Access. 2024;12:161329-161356. doi:10.1109/ACCESS.2024.3477714.
[12] Johnphill O, et al. Self-healing in cyber-physical systems using machine learning: a critical analysis of theories and tools. Future Internet. 2023;15(7):244. doi:10.3390/fi15070244.
[13] Abdullahi I, Longo S, Samie M. Towards a distributed digital twin framework for predictive maintenance in industrial Internet of Things (IIoT). Sensors. 2024;24(8):2663. doi:10.3390/s24082663.
[14] Moosavi S, Farajzadeh-Zanjani M, Razavi-Far R, Palade V, Saif M. Explainable AI in manufacturing and industrial cyber- physical systems: a survey. Electronics. 2024;13(17):3497. doi:10.3390/electronics13173497.
[15] Mikołajewska E, Mikołajewski D, Mikołajczyk T, Paczkowski T. Generative AI in AI-based digital twins for fault diagnosis for predictive maintenance in Industry 4.0/5.0. Appl Sci. 2025;15(6):3166. doi:10.3390/app15063166.
[16] Chinnasamy P, Samrin R, Sujitha BB, Augasthega R, Rajagopal M, Nageswaran A. Integrating intelligent breach detection system into 6G enabled smart grid- based cyber physical systems. Wirel Pers Commun. 2024. doi:10.1007/s11277-024-11192-2.
[17] Cali U, Catak FO, Halden U. Trustworthy cyber- physical power systems using AI: dueling algorithms for PMU anomaly detection and cybersecurity. Artif Intell Rev. 2024;57(7):183. doi:10.1007/s10462-024- 10827-x.
[18] Ryalat M, ElMoaqet H, AlFaouri M. Design of a smart factory based on cyber-physical systems and Internet of Things towards Industry 4.0. Appl Sci. 2023;13(4):2156. doi:10.3390/app13042156.
[19] Abdelrahman MS, Kharchouf I, Hussein HM, Esoofally M, Mohammed OA. Enhancing cyber-physical resiliency of microgrid control under denial-of-service attack with digital twins. Energies. 2024;17(16):3927. doi:10.3390/en17163927.
[20] Nishtar Z, Wang F, Jaskani FH, Afzaal H. Real-time fault detection and isolation in power systems for improved digital grid stability using an intelligent neuro-fuzzy logic. CMES. 2025;143(3):2919-2956. doi:10.32604/cmes.2025.065098.
[21] Wu X, Chen X, Zhang K. Analysis of the monitoring and identification effect of system cognitive service technology on DC system in power grid. Energy Inform. 2025;8(1):116. doi:10.1186/s42162-025- 00569-7.
[22] Al-Anbuky A, Altaf S, Gheitasi A. Cyber-physical distributed intelligent motor fault detection. Sensors. 2024;24(15):5012. doi:10.3390/s24155012.
[23] Shukla A, et al. Intelligent automated fault detection framework for single phase motors using real time monitoring and machine learning. Discov Artif Intell. 2025;5(1):368. doi:10.1007/s44163-025-00509-0.
[24] VVM, SHMP, Satheesh R, Das V, Padmanaban S. AI- driven cybersecurity framework for anomaly detection in power systems. Sci Rep. 2025;15(1):35506. doi:10.1038/s41598-025- 19634-y.
[25] Pillai PK, Devaraj D, Selvam S. Smart diagnostics of AI- powered IoT solutions for solar grid reliability. Discov Electron. 2025;2(1):72. doi:10.1007/s44291- 025-00113-7.
[26] Hosseini SA, Taheri B, Sadeghi SHH, Nasiri A. A deep learning model for fault detection in distribution networks with high penetration of electric vehicle chargers. e-Prime Adv Electr Eng Electron Energy. 2024;10:100845. doi:10.1016/j.prime.2024.100845.
[27] Teta A, et al. Fault detection and diagnosis of grid- connected photovoltaic systems using energy valley optimizer based lightweight CNN and wavelet transform. Sci Rep. 2024;14(1):18907. doi:10.1038/s41598-024-69890-7.
[28] Yang C, Li H, Zeng W, Fan J, Ren Z. Fault detection and classification of power lines based on Bayes- LSTM-attention. Energies. 2025;18(24):6483. doi:10.3390/en18246483.
[29] Tunio NA, Tunio MA, Raza MA, Faheem M, Hashmani AA, Nadeem R. Performance comparison between deep learning models for fault classification in transmission lines using time series data. Energy Sci Eng. 2025;13(5):2330-2351. doi:10.1002/ese3.70033.
[30] Boumkheld N, Deconinck G, Loenders R. Real-time co- simulation for the analysis of cyber attacks impact on distance relay backup protection. EAI Endorsed Trans Energy Web. 2024;11. doi:10.4108/ew.4862.
[31] Khandelwal D, Anand P, Ray M, RG S. Fault detection in electrical power systems using attention-GRU- based fault classifier (AGFC-Net). Sci Rep. 2025;15(1):24133. doi:10.1038/s41598-025-06493-w.
[32] Tunio NA, Hashmani AA, Zuhra FT, Altimania MR, Munir HM, Zaitsev I. Deep learning-based fault classification in extra high voltage transmission lines: a comparative study using simulated and real-time sequential data. Energy Sci Eng. 2026;14(1):201-217. doi:10.1002/ese3.70346.
[33] Liang G, Cui L, Guo J, Li L, Xue G. Power system fault maintenance system based on deep learning algorithm. Procedia Comput Sci. 2025;262:580-587. doi:10.1016/j.procs.2025.05.088.
[34] Mendeley Data. fault_dataset.csv [Internet]. [cited 2026 Jan 30]. Available from: https://data.mendeley.com/datasets/3dvjgvv5bz/2/files /a2604696-b9e9-4a6e-87fa-f706a6a006ad
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Zhuangwei Chen, Beilei Zhang, Qing Jiang, Wenyong Zhong, Haohao Fu
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
