STM Journals Peer-reviewed research from Consortium e-Learning Network

International Journal of Energy and Thermal Applications Original Research

Development of a Generative AI Model for Early Detection and Prevention of Electrical Faults in Thermal Power Plants

  1. Shreekantrao Department of Electrical Engineering, Suresh Gyan Vihar University
  2. Nagendra Kumar Swarnkar Department of Electrical Engineering, Suresh Gyan Vihar University

Abstract

Electrical faults in thermal power plants can lead to severe equipment damage, production downtime, and safety hazards if not detected in advance. This study presents the development of a Generative Artificial Intelligence (GenAI) model for the early detection and prevention of electrical faults using predictive analytics. The proposed framework integrates Generative Adversarial Networks (GANs) with deep learning (CNN) and machine learning algorithms (Random Forest, Logistic Regression) to enhance data diversity, improve classification accuracy, and ensure early fault diagnosis. A comprehensive dataset representing operational parameters—such as voltage, current, temperature, vibration level, load factor, and power factor—was utilized for model training and evaluation. Synthetic data generated through the GAN improved fault representation and model generalization. Experimental results demonstrate that the proposed GAN-CNN hybrid model achieved the highest accuracy of 98.3%, outperforming traditional methods in terms of precision, recall, and F1-score. The feature importance analysis revealed that voltage, current, and temperature were the most influential parameters in predicting potential faults. The findings confirm that the developed Generative AI framework provides a robust, data-driven, and proactive solution for predictive maintenance and fault prevention in thermal power plants. This approach not only reduces unplanned downtime but also enhances system reliability, safety, and operational efficiency — marking a significant step toward intelligent and self-healing power systems.

Keywords

References (15)

  1. Khalid S, Song J, Raouf I, Kim HS. Advances in Fault Detection and Diagnosis for Thermal Power Plants: A Review of Intelligent Techniques. Mathematics. 2023;11(8):1767. doi:10.3390/math11081767
  2. Sun, X. Liu, M. Lin, J. Wang, T. Jiang, and Y. Wang, “Transmission line fault diagnosis method based on improved multiple SVM model,” IEEE Access, vol. 11, pp. 133825–133834, 2023.
  3. -M. Li, S.-C. Chu, X. Shao, and J.-S. Pan, “A single-phase-to-ground fault location method based on convolutional deep belief network,” Electric Power Systems Research, vol. 209, p. 108044, 2022.
  4. Hichri, M. Hajji, M. Mansouri, K. Abodayeh, K. Bouzrara, H. Nounou, and M. Nounou, “Genetic-algorithm-based neural network for fault detection and diagnosis: Application to grid-connected photovoltaic systems,” Sustainability, vol. 14, p. 10518, 2022.
  5. Ismail FB, Al-Kayiem HH, Kazem HA. AI Adoption for Steam Boiler Trip Prevention in Thermal Power Plants. International Journal of Energy Production and Management. 2024;9(3):131-142. doi:10.18280/ijepm.090302
  6. Kanwal and S. Jiriwibhakorn, “Artificial intelligence based faults identification, classification, and localization techniques in transmission lines—A review,” IEEE Latin America Transactions, vol. 21, pp. 1291–1305, 2023.
  7. R. Nayeri, B. Araabi, and B. Moshiri, “Fault detection and isolation of gas turbine: Hierarchical classification and confidence rate computation,” Journal of the Franklin Institute, vol. 359, no. 17, pp. 10120–10144, 2022.
  8. Liu Y, Li P, Si Y, Ma L. A Comprehensive Review of AI Integration for Fault Detection in Modern Power Systems: Data Processing, Modeling, and Optimization. Energies. 2025;18(18):4983. doi:10.3390/en18184983
  9. K. Shukla and K. Deepa, “Deep learning techniques for transmission line fault classification—A comparative study,” Ain Shams Engineering Journal, vol. 15, no. 9, 2024.
  10. Mnyanghwalo, H. Kundaeli, E. Kalinga, and N. Hamisi, “Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparison,” Cogent Engineering, vol. 7, p. 1857500, 2021.
  11. Mishra M, Singh JG. A comprehensive review on deep learning techniques in power system protection: Trends, challenges, applications and future directions. Results in Engineering. 2025;25:103884. doi:10.1016/j.rineng.2024.103884
  12. Sepúlveda-Oviedo EH, Travé-Massuyès L, Subias A, Pavlov M, Alonso C. Fault diagnosis of photovoltaic systems using artificial intelligence: A bibliometric approach. Heliyon. 2023;9(11):e21491. doi:10.1016/j.heliyon.2023.e21491
  13. Martinez-Velasco JA, Serrano-Fontova A, Bosch-Tous R, Casals-Torrens P. A Bibliographical Survey on Fault Detection, Classification and Location Methods in Power Systems Using Artificial Intelligence. 2025. doi:10.20944/preprints202504.1794.v1
  14. De La Cruz, E. Gómez-Luna, M. Ali, J. C. Vasquez, and J. M. Guerrero, “Fault location for distribution smart grids: Literature overview, challenges, solutions, and future trends,” Energies, vol. 16, no. 5, p. 2280, 2023.
  15. Shafiullah, K. A. AlShumayri, and M. S. Alam, “Machine learning tools for active distribution grid fault diagnosis,” Advances in Engineering Software, vol. 173, p. 103279, 2022.