Design of intelligent inspection system for 500 kV substation based on multi-source data fusion
DOI:
https://doi.org/10.4108/ew.13195Keywords:
multi-source data fusion, 500 kV substation, intelligent inspection, deep learning; state estimationAbstract
INTRODUCTION: The safe and stable operation of 500 kV substations is essential for ensuring power grid reliability. Traditional manual inspection methods suffer from low efficiency, limited coverage, and poor real-time performance, making intelligent inspection technologies increasingly important.
OBJECTIVES: This study aims to develop an intelligent inspection system for 500 kV substations based on multi-source data fusion to improve equipment status monitoring, fault diagnosis, and operational reliability.
METHODS: The proposed system integrates infrared thermal images, visible-light images, sound signals, and vibration data for comprehensive equipment perception. A multi-modal deep learning network with an attention mechanism (AMM-Net) is designed for adaptive feature extraction. In addition, pixel-level, feature-level, and decision-level fusion strategies are combined with a trust-based distributed Kalman filtering algorithm (Trust-DKF) to improve robustness and anti-interference capability.
RESULTS: Experimental results show that the system achieves 94.7% accuracy and 93.1% F1-score in equipment status recognition. Under noise and occlusion interference, performance decreases by only 10.7%. The edge-device inference time is optimized to 28.9 ms with low energy consumption of 0.12 J per operation.
CONCLUSION: The proposed system significantly improves the efficiency, accuracy, and reliability of intelligent substation inspection.
Downloads
References
[1] Li Z, Zhang Y, Wu H, Suzuki S, Namiki A, Wang W. Design and application of a UAV autonomous inspection system for high-voltage power transmission lines. Remote Sens. 2023;15(3):865-877.
[2] Chen DQ, Guo XH, Huang P, Li FH. Safety distance analysis of 500kv transmission line tower uav patrol inspection. IEEE Lett Electromagn Compat Pract Appl. 2020;2(4):124-128.
[3] Xu C, Li Q, Zhou Q, Zhang S, Yu D, Ma Y. Power line-guided automatic electric transmission line inspection system. IEEE Trans Instrum Meas. 2022;71:1-18.
[4] Gao H, Dekyi D, Metok M. Efficient unmanned aerial vehicle inspection and management of transmission lines in modern electric power enterprises. Energy Informatics. 2025;8(1):117-128.
[5] Zhang C, Zhang C, Cui H, Li P, Wan Y, Sun D, Ma H. Embodied intelligence-driven framework for UAV power inspection systems: Federated reinforcement learning for multi-agent collaborative optimization. In: International Conference on Intelligent Computing. Singapore: Springer Nature Singapore; 2025. p. 292-301.
[6] De Albuquerque JMN, Neto OR, Armênio GF, Correa VM, Do Valle DRG, Domingues A, De Oliveira AS. A Novel Method for Multi-Modal Predictive Inspection of Power Lines. IEEE Access. 2024.
[7] Rong S, He L, Du L, Li Z, Yu S. Intelligent detection of vegetation encroachment of power lines with advanced stereovision. IEEE Trans Power Deliv. 2020;36(6):3477-3485.
[8] Zhang Y, Li D, Chen Y, Liu G, Fan D, Li W, Mai X. Research on Electric Field Safety Distance of High-Voltage Equipment in Substations Inspected by UAV. In: International Symposium on Insulation and Discharge Computation for Power Equipment. Singapore: Springer Nature Singapore; 2023. p. 505-513.
[9] Xu L, Guo H, Fu Y, Wang Z, Li Z, Hua Z, Liu S. Research of 3D trajectory hovering points determination method of UAV patrol inspection transmission tower. J Phys Conf Ser. 2022;2378(1):012088.
[10] Li X, Zhang J, Zhang L, Chen X. Layout Optimization and Multi-scenes Intelligent Inspection Scheme Design Based on Substation Video Monitoring. J Phys Conf Ser. 2023;2560(1):012022.
[11] Xuefeng N, Yao G. Design of intelligent operation inspection platform based on the multi-agent system for live line measurement of substation. J Phys Conf Ser. 2022;2401(1):012088.
[12] Wang S, Dong S, Lv K, Zhang L, Ling Z, Xi Y. Architecture research of novel digital intelligent substation system. In: 2023 4th International Conference on Computer Engineering and Application (ICCEA). IEEE; 2023. p. 229-233.
[13] Zhong L, Xie Z, Wang K, Ting L, Chen D. Research on robot for repairing broken strands in 500kV High Voltage Live Operation. J Phys Conf Ser. 2021;2030(1):012088.
[14] Liu Y, Fan S. An improved slam algorithm for substation inspection robots based on 3d lidar and visual information fusion. Energies. 2025;18(11):2797-2806.
[15] Lei T, Lv F, Liu J, Zhang L, Zhou T. Research on fault detection algorithm of electrical equipment based on neural network. Math Probl Eng. 2022;2022:9015796-9015806.
[16] Li C, Shi F, Liu M, Wang Y, Zhang W, Li C. An intelligent diagnosis method for analog of the secondary equipment based on the remote dispatching station. In: 2022 7th Asia Conference on Power and Electrical Engineering (ACPEE). IEEE; 2022. p. 2229-2233.
[17] Pei S, Sun H. Structural design and simulation study of intelligent defect elimination equipment for high-voltage transmission line pin defects. IET Gener Transm Distrib. 2023;17(24):5366-5377.
[18] Lei H, Haining X, Lingbin S, Qiang J, Qingye S. Design and Application of New Technology for Intelligent Inspection and Early Warning of Submarine Cables against External Breakage. In: 2024 4th Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS). IEEE; 2024. p. 696-701.
[19] Gan X, Geng X, Xiong Z, Wu Z, Du S, Gao Y, Guo Y. Application of 5G communication technology on intelligent inspection in 750kV substation. J Phys Conf Ser. 2021;1983(1):012089.
[20] Liu J, Zhao Z, Ji J, Hu M. Research and application of wireless sensor network technology in power transmission and distribution system. Intell Converg Netw. 2020;1(2):199-220.
[21] Li Z, Yoshie O, Wu H, Mai X, Yang Y, Qu X. Image analysis method of substation equipment status based on cross-modal learning. IEEJ Trans Electr Electron Eng. 2024;19(9):1507-1521.
[22] Meng R, Wang ZL, Zhao ZL, Li JP, Fu WP, Zhong S. A multimodal detection method for UHV substation faults based on robot inspection and deep learning. J Robot. 2022;2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yaoshan Zhang, Zhiqiang Xiao, Zhihua Lin, Xiuquan Hu, Yue Zhou
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
