Detection of Chronic Load Imbalance and Hot-Spot Risk in Building Electrical Systems using Long-Term Three-Phase Current Analysis and Mechanism-Informed Artificial Intelligence
Article Sidebar
Main Article Content
Abstract
Infrared thermography detects hot spots only at the time of inspection, whereas electrical system degradation evolves continuously through the 24/7 accumulation of operational stress. This study proposes a novel mechanism-informed predictive monitoring framework that integrates long-term three-phase current data with a physics-guided machine-learning inference model to identify early degradation signatures before infrared-detectable heating occurs. Results synthesized from multiple degradation indicators reveal that Phase B exhibits persistent structural dominance, with a mean occupancy of 56% (peaking at 71%), and accumulates 2.35 times the thermal debt of Phase A. This imbalance produces pronounced thermal memory, whereby 38% of thermal stress remains unrecovered after load reduction, resulting in the fastest insulation aging (aging rate = 0.0028; final Aging Index = 0.95). Notably, the proposed system degradation collapse index exceeds the critical degradation threshold (0.70) despite the absence of overload or fault conditions under conventional protection criteria. The proposed framework provides a continuous, low-cost, and practical solution for 24/7 predictive condition monitoring, enabling electrical hazards to be identified before hot spots and failures occur while overcoming the limitations of snapshot-based inspections.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The content and information in the article published in Journal of Rajamangala University of Technology Srivijaya It is the opinion and responsibility of the author of the article. The editorial journals do not need to agree. Or share any responsibility.
References
Abdolahi, M., Song, W. and Yazdani-Asrami, M. 2026. Intelligent condition monitoring of power cables using advanced machine learning models. Results in Engineering 29: 108371.
Ahmad, S., Rizvi, Z.H. and Wuttke, F. 2025. Unveiling soil thermal behavior under ultra-high voltage power cable operations. Scientific Reports 15(1): 7315.
Al-Dulaimi, A.A., Guneser, M.T., Hameed, A.A., Márquez, F.P.G. and Gouda, O.E. 2024. Adaptive FEM–BPNN model for predicting underground cable temperature considering varied soil composition. Engineering Science and Technology, an International Journal 51: 101658.
Saleh, M.A., Alquennah, A.N., Ghrayeb, A., Refaat, S.S., Abu-Rub, H. and Khatri, S.P. 2025. A review on the lifetime estimation methods of XLPE power cables. IEEE Open Journal of Industry Applications 6: 445–489.
Choudhary, M., Shafiq, M., Kiitam, I., Hussain, A., Palu, I. and Taklaja, P. 2022. A review of aging models for electrical insulation in power cables. Energies 15(9): 3408.
Enescu, D., Colella, P. and Russo, A. 2020. Thermal assessment of power cables and impacts on cable current rating: An overview. Energies 13(20): 5319.
Hu, J., Li, Y., Liu, Y. and Liu, H. 2025. Analysis of thermal-mechanical effect in XLPE cables based on COMSOL, 31–41. In Penza, M. and Wang, S. Third International Conference on Advanced Materials and Equipment Manufacturing (AMEM 2024), Vol. 13691. SPIE, Bellingham, Washington, USA.
Rasoulpoor, M., Mirzaie, M. and Mirimani, S.M. 2017. Thermal assessment of sheathed medium voltage power cables under non-sinusoidal current and daily load cycle. Applied Thermal Engineering 123: 353–364.
Huang, L.C., Chang, H.C., Chen, C.C. and Kuo, C.C. 2011. A ZigBee-based monitoring and protection system for building electrical safety. Energy and Buildings 43(6): 1418–1426.
Oelhaf, J., Kordowich, G., Pashaei, M., Bergler, C., Maier, A., Jäger, J. and Bayer, S. 2025. A scoping review of machine learning applications in power system protection and disturbance management. International Journal of Electrical Power & Energy Systems 172: 111257.
Pan, J., Liu, J., Chen, X. and Zhong, K. 2021. Three-phase unbalanced load control based on load–electricity transfer index. Energy Reports 7: 312–319.
Ruiz, M. and Betancourt, C. 2026. Thermographic diagnosis of corrosion-driven contact degradation in power equipment using infrared imaging and color-channel decomposition. Energies 19(3): 766.
Shao, Q., Fan, S., Zhang, Z., Liu, F., Fu, Z., Lv, P. and Mu, Z. 2025. Artificial intelligence in cable fault detection and localization: Recent advances and research challenges. Energies 18(14): 3662.
Tao, J., Rehman, S.U., Ali, R. and Raza, S.A. 2025. Advancement and challenges: A review of power cable aging monitoring and diagnostic techniques. Renewable and Sustainable Energy Reviews 222: 115970.
Theofanous, A., Ullah, I., Galea, M., Giangrande, P., Madonna, V., Ji, Y., Licari, J. and Apap, M. 2025. Modelling of insulation thermal ageing: Historical evolution from fundamental chemistry towards becoming an electrical machine design tool. Energies 18(23): 6087.
Wu, Y., Sicard, B. and Gadsden, S.A. 2024. Physics-informed machine learning: A comprehensive review on applications in anomaly detection and condition monitoring. Expert Systems with Applications 255: 124678.
Zhang, Z., Deng, X., Liang, L., Wang, X., Chen, Y. and Ruan, J. 2024. Temperature field calculation and thermal circuit equivalent analysis of 110 kV core cable joint. Processes 12(3): 463.
