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

International Journal of Energy and Thermal Applications Original Research

Enhancing Maintenance Decision-Making in Thermal Power Plants Using Generative AI-Based Fault Diagnosis

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

Abstract

The growing complexity of operation and power consumption of thermal power stations involve the need to have intelligent fault diagnosis systems that can be used to guarantee reliability and safety in operation. In this research, a Generative AI (GenAI)-based hybrid architecture of early fault detection and predictive maintenance is proposed to improve the decision-making process of the maintenance team. The data-driven analytic approach combines methods of data-driven analytics, Generative AI models, and supervised learning algorithms including Long Short-Term Memory (LSTM), Random Forest (RF), and XGBoost. The sensor data of plant components such as voltage, current, temperature and vibration are first pre-processed and feature engineered to come up with important fault indicators. Exploratory Data Analysis (EDA) indicates that there are correlations between the operational stress and fault occurrence. The Generative AI module enhances the dataset by generating rare fault samples, which solve the issue of data imbalance and enhance the learning robustness. Models that were trained on this better dataset exhibit a high level of accuracy, precision and reliability of fault prediction. Experimental findings indicate that, the GenAI-augmented Random Forest model had the best performance of 97.2% accuracy and 96% F1-score, which was better than the traditional approaches. The created framework allows real-time forecast of faults, active maintenance planning, and significant minimization of unplanned downtime. The study will help to develop intelligent and data-driven maintenance systems to reach Industry 4.0 goals of digitalizing power stations and making them sustainable.

Keywords

References (14)

  1. Bunyan ST, Khan ZH, Al-Haddad LA, Dhahad HA, Al-Karkhi MI, Ogaili AAF, et al. Intelligent Thermal Condition Monitoring for Predictive Maintenance of Gas Turbines Using Machine Learning. Machines. 2025;13(5):401. doi:10.3390/machines13050401
  2. Y. Arafat, M. J. Hossain, and M. M. Alam, “Machine learning scopes on microgrid predictive maintenance: Potential frameworks, challenges, and prospects,” Renewable and Sustainable Energy Reviews, vol. 190, p. 114088, 2024.
  3. 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
  4. Gawde, S. Patil, S. Kumar, P. Kamat, K. Kotecha, and S. Alfarhood, “Explainable predictive maintenance of rotating machines using LIME, SHAP, PDP, ICE,” IEEE Access, vol. 12, pp. 29345–29361, 2024.
  5. D. Scaife, “Improve predictive maintenance through the application of artificial intelligence: A systematic review,” Results in Engineering, vol. 21, p. 101645, 2023.
  6. Hundi and R. Shahsavari, “Comparative studies among machine learning models for performance estimation and health monitoring of thermal power plants,” Applied Energy, vol. 265, p. 114775, 2020.
  7. Cazacu E, Petrescu LG, Ioniță V. Smart Predictive Maintenance Device for Critical In-Service Motors. Energies. 2022;15(12):4283. doi:10.3390/en15124283
  8. Department of Mechatronics Engineering, Federal University Otuoke, Bayelsa State, Nigeria, Ujam CJ, Adeniyi D. A, Department of Electrical and Electronic Engineering, Federal University, Otuoke, Bayelsa State, Nigeria. Enhancing Power System Reliability Through Advanced Fault Diagnosis Methods: A Deep Learning Approach. Engineering and Technology Journal. 2024;09(05). doi:10.47191/etj/v9i05.13
  9. Divya D, Marath B, Santosh Kumar MB. Review of fault detection techniques for predictive maintenance. Journal of Quality in Maintenance Engineering. 2022;29(2):420-441. doi:10.1108/jqme-10-2020-0107
  10. Dong L, Chen N, Liang J, Li T, Yan Z, Zhang B. A review of indoor-orbital electrical inspection robots in substations. Industrial Robot: the international journal of robotics research and application. 2022;50(2):337-352. doi:10.1108/ir-06-2022-0162
  11. Gao H, Wang Z, Tang A, Han C, Guo F, Li B. Research on Series Arc Fault Detection and Phase Selection Feature Extraction Method. IEEE Transactions on Instrumentation and Measurement. 2021;70:1-8. doi:10.1109/tim.2021.3080376
  12. Gursel E, Reddy B, Khojandi A, Madadi M, Coble JB, Agarwal V, et al. Using artificial intelligence to detect human errors in nuclear power plants: A case in operation and maintenance. Nuclear Engineering and Technology. 2023;55(2):603-622. doi:10.1016/j.net.2022.10.032
  13. Inwanna W, Mongkolsatitpong S, Chancharoensook P, Pattanadech N. A Locating Diagnosis of Partial Discharge on Cross-bonding Ground System. 2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON). 2021:52-55. doi:10.1109/ecti-con51831.2021.9454781
  14. Ismail RIB, Ismail Alnaimi FB, AL-Qrimli HF. Artificial Intelligence Application in Power Generation Industry: Initial considerations. IOP Conference Series: Earth and Environmental Science. 2016;32:012007. doi:10.1088/1755-1315/32/1/012007