Intelligent Fault Diagnosis for Power Plant Arrester based on Reinforcement Learning and Condition Monitoring Data_Vol. 3 No. 4 (JBDC 2025)_Journal of Big Data and Computing (ISSN: 2959-0590)

Home > Journal of Big Data and Computing (ISSN: 2959-0590) > Vol. 3 No. 4 (JBDC 2025) >

Intelligent Fault Diagnosis for Power Plant Arrester based on Reinforcement Learning and Condition Monitoring Data

Download PDF

DOI: https://doi.org/10.62517/jbdc.202501426

Author(s)

Guanqi Li*, Zhenyu Wang, Yupei Yang, Yongtao Wang, Fan Li, Yanan Li, Hui Li, Yuan Gao, Yuan Wang, Gong Cheng

Affiliation(s)

State Grid Linzhou Power Supply Company, Linzhou, Henan, China *Corresponding Author

Abstract

This paper proposes an intelligent fault diagnosis method for High-Voltage Arresters utilizing Live Online Monitoring data, addressing the complexity and latency of traditional diagnosis. The core of the method is a reinforcement learning model: it employs a Deep Q-Network (DQN) for state feature extraction and integrates the SARSA algorithm for real-time identification of arrester fault states. Furthermore, Monte Carlo Tree Search (MCTS) is introduced to enhance the attribution analysis of fault causes, thereby improving the depth and reliability of the diagnosis. Experimental results demonstrate that this approach achieves high-accuracy diagnosis (96.5%) across various fault types and exhibits fast response capability (0.45 s), providing an effective path for the intelligent analysis of abnormal data, such as Leakage Current.

Keywords

Reinforcement Learning (RL); Power Plant Arrester; Fault Diagnosis; Deep Q-Network (DQN); SARSA; Monte Carlo Tree Search (MCTS); Live Online Monitoring; Leakage Current

References

[1]S. Abulanwar, M. E. M. Rizk, W. Hu, Z. Chen and A. Ghanem, "Novel Zonal Fault Detection Scheme for DC Wind Farm via Disposition of Surge Arresters in Multipurpose Grounding System," in IEEE Transactions on Power Delivery, 2024, 39(1): 245-260. [2]C. Alexander, P. Mikhail, I. Dmitryi and V. Frolov, "Effects of high altitude on multi-chamber arrester performance," 2021 35th International Conference on Lightning Protection (ICLP) and XVI International Symposium on Lightning Protection (SIPDA), Colombo, Sri Lanka, 2021, pp. 01-04. [3]J. Bai, X. Zhou, T. Tian, L. Yan, M. Yunlong and L. Weifeng, "Study on Fault Diagnosis of Metal Oxide Surge Arrester Based on Infrared Detection and Leakage Current Detection," 2022 7th Asia Conference on Power and Electrical Engineering (ACPEE), Hangzhou, China, 2022, pp. 1766-1770. [4]H.L Chen; C. Li; J. Bai, et al., "Analysis of a New Method for Evaluating Lightning Trip-Out Fault Rate in Active Distribution Networks," 2024 International Conference on Artificial Intelligence and Power Systems (AIPS), Chengdu, China, 2024, pp. 78-82. [5]F. Giraudet, "Rationales and Expectations with Upcoming New Line Surge Arrester (LSA) Standard IEC/IEEE 60099-11," 2025 13th Asia-Pacific International Conference on Lightning (APL), Bali, Indonesia, 2025, pp. 1-5. [6]B. B. S. D. A. Harsono, P. A. A. Pramana and Sriyono, "A Concept for Overhead Transmission Line Performance Evaluation toward Lightning Strikes," 2022 International Conference on Technology and Policy in Energy and Electric Power (ICT-PEP), Jakarta, Indonesia, 2022, pp. 106-110. [7]F. Li, K. Li, B. Du, B. Jiang and W. Li, "Study of the Technology of On-Line Monitoring for Transmission Lines Arresters by Measurement of Lightning Current and Leakage Current," 2024 IEEE 2nd International Conference on Sensors, Electronics and Computer Engineering (ICSECE), Jinzhou, China, 2024, pp. 432-436. [8]Long J, Yang M, Chen Y, Liu K, Zhang J, Zhang J, et al. Inverter Nonlinearity Compensation Method for SPMSM Drives based on Accurate Voltage Error Calculation. Proceedings of the CSEE, 2022, 42 (17): 6425-6436. [9]K. Michishita, T. Omura, S. Yokoyama, K. Takano, M. Ikuta and M. Matsui, "Arrester Damage on 6.6 kV Power Distribution Line in Japan by Winter Lightning," 2021 35th International Conference on Lightning Protection (ICLP) and XVI International Symposium on Lightning Protection (SIPDA), Colombo, Sri Lanka, 2021, pp. 01-04. [10]B. Normoyle, J. L. De Franco, D. White, J. Roberts, S. Wiseman and B. Johnnerfelt, "Sentinel, Fast detection of faulted Transmission Line Arresters," 2020 IEEE/PES Transmission and Distribution Conference and Exposition (T&D), Chicago, IL, USA, 2020, pp. 1-5. [11]D. Paul, P. E. Sutherland, C. S. Mardegan and P. Lewin, "Update on Transient Surge Arresters (SA) and Insulators at Medium-Voltage Power Distribution System," in IEEE Transactions on Industry Applications, 2025, 61(4): 5962-5970. [12]I. R. Pordanjani, X. Liang, Y. Wang and A. Schneider, "Single-Phase Ferroresonance in an Ungrounded System Causing Surge Arresters Failure during the System Energization," 2021 IEEE/IAS 57th Industrial and Commercial Power Systems Technical Conference (I&CPS), Las Vegas, NV, USA, 2021, pp. 1-8. [13]S. Refiasto, B. Denov, S. Suwarno and R. Zoro, "Installation of Multi Chamber Arrester to Improve Lightning Reliability Performance of Distribution Lines System in Oil and Gas Area," 2021 3rd International Conference on High Voltage Engineering and Power Systems (ICHVEPS), Bandung, Indonesia, 2021, pp. 258-262. [14]C. Sakakibara, K. Michishita, K. Takano and H. Nakata, "A Proposal of an Estimation Method for Identifying Return Strokes Causing Surge Arrester Burnout Faults on Actual Distribution Line," in IEEE Transactions on Power Delivery, doi: 10.1109/TPWRD.2025.3609862., pp:1-12. [15]C. E. Sălceanu, D. Iovan, M. Ionescu, D. C. Ocoleanu and Ş. Şeitan, "Analysis on the Behaviour of 36 kV, 10 kA Pre-failed Polymer Surge Arrester at Short-Circuit Current," 2024 International Conference on Applied and Theoretical Electricity (ICATE), Craiova, Romania, 2024, pp. 1-6. [16]Shan P, Sun Y, Song Y, et al. Adaptive Parameter Tuning and Virtual Impedance Injection Control for Coupled Harmonic Mitigation of Photovoltaic Converter. IEEE Trans. Power Electron., 2025, 40(1): 162-175. [17]Z. Sitong, Z. Shuaida, B. Yuwei and W. Shuai, "Analysis of the 500kV Line Arrester Exploion Accident," 2023 IEEE 7th Conference on Energy Internet and Energy System Integration (EI2), Hangzhou, China, 2023, pp. 3930-3933. [18]H. A Tan; S. Guo; Y. He, et al., "Simulation study on lightning protection of 35kV transmission line and selection of surge arrester valve parameter based on ATP-EMTP," 2024 4th International Conference on Intelligent Power and Systems (ICIPS), Yichang, China, 2024, pp. 834-837. [19]J. Wang, P. Dai and W. Yu, "Optimal Observation Policy of Fault Diagnosis: A Reinforcement Learning Approach," 2020 Chinese Automation Congress (CAC), Shanghai, China, 2020, pp. 7206-7210. [20]R. Yin, X. Yang, Y. Chen and H. Yuan, "Impact of complex working conditions caused by the superposition of photovoltaic access and system short circuit on the operation of distribution network surge arresters," 2024 8th International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE), Xi'an, China, 2024, pp. 942-945. [21]Y. Zhao and J. O'Leary, "Solving Large Fault Trees with Importance Sampling and Tree Search," 2024 Annual Reliability and Maintainability Symposium (RAMS), Albuquerque, NM, USA, 2024, pp. 1-6. [22]L. Zhang, Z. Zhang, A. S. Bretas and V. A. Rakov, "A Reliability-based Optimization Model for Lightning Protection System Design of Distribution Networks," 2020 52nd North American Power Symposium (NAPS), Tempe, AZ, USA, 2021, pp. 1-6.