FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-140121

Research Article |

Intelligent Thermal Protection of Power Transformers Using ANN–FLC Framework for Smart Grid Applications

Author(s): Salem Idham Ewad1*, Mohammed Brayyich2, and Adnan Shadhir Mutlaq3

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 14, Issue 1

Publisher : FOREX Publication

Published : 30 March 2026

e-ISSN : 2347-470X

Page(s) : 200-206

DOI: https://doi.org/10.37391/IJEER.140121

Abstract

Transformer lifetime is greatly impacted by thermal stress under overload conditions, while traditional threshold-based protection and delayed cooling may react only after the hottest-spot temperature has already progressed to a critical stage. This study presents an adaptive framework to that combines ANN–FLC control with nanofluid cooling and Lyapunov-guided gain adaptation, while quantifying insulation loss of life based on the IEEE C57.91-2011 loading guide. The approach is evaluated on a 400 kVA, 33/0.38 kV, ONAN transformer under challenging conditions (40°C ambient, up to 140% overload, 5.2% THD, and a 15°C thermal step) each experiment was repeated five times (N = 1200 samples, 30 ms sampling). In comparison with ON–OFF, PID, and conventional ANN–FLC controllers. The proposed approach yields a faster transient response (28 s settling, 2.3°C overshoot), maintains operation within the 120°C limit, and decreasing aging-related indices. Long-period trajectories further present improved correlation aging and a projected insulation life of 32.4 years, enabling proactive operation/management, stability-aware transformer protection for intelligent-grid asset lifecycle management.

Keywords: Transformer, ANN, FLC, Protection, Smart Grid.




Salem Idham Ewad, Assistant Lecturer, Department of Electrical Engineering, University of Thi-Qar, Iraq; Email: salem.idham@utq.edu.iq

Mohammed Brayyich, Assistant Lecturer, Department of Electrical Engineering, University of Thi-Qar, Iraq; Email: m.r.brayyich@utq.edu.iq

Adnan Shadhir Mutlaq, Assistant Lecturer, Department of Electrical Engineering, University of Thi-Qar, Iraq; Email: adnan.shadhir@utq.edu.iq

    [1] Hao, Y., Zhang, Y., & Li, P. (2024). Inversion method for transformer winding hot-spot temperature based on SA-GRU model. Energy Reports, 10, 104328. https://doi.org/10.1016/j.egyr.2024.04.028
    [2] Zhang, N., Liu, Q., Wang, M., & Zhao, F. (2024). Monitoring of transformer hotspot temperature using a wireless mesh network and SVR. Energies, 17(24), 6266. https://doi.org/10.3390/en17246266.
    [3] Lessinger, S., Müller, P., & Hofmann, L. (2025). Aging assessment of power transformers with data science. Energies, 18(15), 3960. https://doi.org/10.3390/en18153960.
    [4] lomgren, E. M. V. (2023). Grey-box modeling for hot-spot temperature prediction of power transformers. Electric Power Systems Research, 229, 109933. https://doi.org/10.1016/j.epsr.2023.109933
    [5] Biswal, B., Deb, S., Datta, S., Ustun, T. S., & Cali, U. (2024). Review on smart grid load forecasting for energy management using machine learning and deep learning techniques. Energy Reports, 10, 653–672https://doi.org/10.1016/j.egyr.2024.09.056.
    [6] Wazir, M. H., Mat Said, D., Md Sapari, N., & Mohd Yassin, Z. I. (2025). Electro-thermal modeling of distribution transformer for hottest-spot evaluation under PV-induced harmonics. International Journal of Renewable Energy Development, 14(3), 450–462. https://doi.org/10.61435/ijred.2025.60959.
    [7] Li, D., Zhao, X., & Wang, Y. (2025). Digital analysis method of transformer hot-spot temperature based on two-way coupling flow–thermal model. IET Electrical Power Applications, 19(4), 1–12. https://doi.org/10.1049/elp2.70018.
    [8] Makacha, J. M. (2025). An integrated fuzzy logic approach for valuation of power transformers (DOH/DOF). Engineering Reports, 7(3), 117030. https://doi.org/10.1002/eng2.117030.
    [9] Singh, A. R., Kumar, D., & Patel, R. (2025). A deep learning and IoT-driven framework for real-time fault prediction in smart grids. Scientific Reports, 15, 2649. https://doi.org/10.1038/s41598-025-02649-w.
    [10] Mohsen, S., Bajaj, M., Kotb, H., & Ghoneim, S. S. M. (2023). Efficient artificial neural network for smart grid stability prediction. International Transactions on Electrical Energy Systems, 33(4), e9974409. https://doi.org/10.1155/2023/9974409.
    [11] Mharakurwa, E. T., Ndlovu, M., & Zhou, T. (2024). Transformer hot-spot temperature estimation through ANFIS model. Heliyon, 10(7), e23941. https://doi.org/10.1016/j.heliyon.2024.e23941.
    [12] Yang, L., Chen, S., & Guo, F. (2025). A transformer oil temperature prediction method based on hybrid numerical and data-driven techniques. Processes, 13(2), 302. https://doi.org/10.3390/pr13020302.
    [13] Prakash, A., Verma, S., & Das, P. (2024). Hybrid ANN–FLC-based control for improved transformer cooling. Journal of Electrical Engineering & Technology, 19(2), 234–245. https://doi.org/10.1007/s42835-024-01429-8.
    [14] Kimura, H., Takahashi, T., & Sato, Y. (2024). Energy-efficient fuzzy logic cooling of distribution transformers. Energy Conversion and Economics, 5(1), 58–70. https://doi.org/10.3390/ece5010058.
    [15] Kumar, N., Sharma, V., & Gupta, R. (2023). Thermal modeling and ANN optimization for transformer hot-spot control. Electric Power Components and Systems, 51(9), 1125–1142. https://doi.org/10.1080/15325008.2023.2287025.
    [16] Sousa, R., Pereira, J., & Almeida, F. (2023). Fuzzy-based control for transformer thermal performance in hybrid renewable grids. Renewable Energy Focus, 45, 102–114. https://doi.org/10.1016/j.ref.2023.04.008.
    [17] Khan, MA Masud, Roksana Haque, and Ammar Bajwa. "A Systematic Literature Review on Energy-Efficient Transformer Design For Smart Grids." American Journal of Scholarly Research and Innovation 1.01 (2022): 186-219.
    [18] Taksana, Radomboon, et al. "Design of Power Transformer Fault Detection of SCADA Alarm Using Fault Tree Analysis, Smooth Holtz–Winters, and L-BFGS for Smart Utility Control Centers." IEEE Access (2024).
    [19] Ahmad, Azniza, et al. "Adaptive ANN based differential protective relay for reliable power transformer protection operation during energisation." IAES International Journal of Artificial Intelligence 8.4 (2019): 307
    [20] da Costa Souza, João Pedro, et al. "A comprehensive review on artificial intelligence-based applications for transformer thermal modeling : Background and perspectives." IEEE Access (2024).

Salem Idham Ewad, Mohammed Brayyich, Adnan Shadhir Mutlaq (2026), Intelligent Thermal Protection of Power Transformers Using ANN–FLC Framework for Smart Grid Applications. IJEER 14(1), 200-206. DOI: 10.37391/IJEER.140121.