Research and Implementation of Intelligent Fault Report Generation Technology for Earthquake Emergency Response in Regional Power Grids
DOI:
https://doi.org/10.4108/ew.14132Keywords:
Earthquake emergency response, power grid fault, intelligent report generation, multimodal language model, slot filling, automated systemAbstract
INTRODUCTION: Earthquake-induced disturbances require fast, standardized fault reports to support regional power-grid emergency response.
OBJECTIVES: To automate report drafting while improving terminology, structure, and traceability compared with manual writing and simple template filling.
METHODS: We design a workflow that combines slot filling, metadata-driven image proxy summarization, and controlled prompt-driven paragraph generation, then assembles outputs into a standardized report template and software system.
RESULTS: On public earthquake and outage datasets, the proposed method outperforms baseline template filling (BLEU-4 1.00 vs 0.37, ROUGE-L 0.90 vs 0.50, BERTScore 0.93 vs 0.85, field coverage 1.00 vs 0.75) and reduces end-to-end report production from ~180 min (manual) to 2 min 15 s.
CONCLUSION: The system enables reliable, high-efficiency fault report generation for earthquake emergency response in regional power grids, with clear potential for deployment.
Downloads
References
[1] Tonnelier M, Delforge D, Below R, Munguía JAT, Saegerman C, Wathelet V, et al. What makes an epidemic a disaster: the future of epidemics within the EM-DAT International Disaster Database. BMC Public Health. 2025;25(1):21.
[2] Amaratunga D, Anzellini V, Guadagno L, Hagen JS, Komac B, Krausmann E, et al. United Nations office for disaster risk reduction regional assessment report on disaster risk reduction 2023: Europe and Central Asia. 2023.
[3] Mate A, Hagan T, Cotilla-Sanchez E, Brekken TK, Von Jouanne A, editors. Impacts of earthquakes on electrical grid resilience. 2021 IEEE/IAS 57th Industrial and Commercial Power Systems Technical Conference (I&CPS); 2021: IEEE.
[4] Hsu C-W, Mostafavi A. Untangling the relationship between power outage and population activity recovery in disasters. Resilient Cities and Structures. 2024;3(3):53-64.
[5] Yoo T-H, Park H. Modeling of power system resilience during a catastrophic disaster and application of the model. IEEE Access. 2024;12:81550-66.
[6] Işık İ, Gol EA. Field teams coordination for earthquake-damaged distribution system energization. Reliability Engineering & System Safety. 2024;245:110050.
[7] Arpali OY, Yilmaz UC, Erkal BG, Gol EA, Gol M. MDP based real time restoration for earthquake damaged active distribution systems. Electric power systems research. 2023;218:109230.
[8] Mille S, Casamayor G, Grivolla J, Shvets AV, Wanner L, editors. Automatic Multilingual Incident Report Generation for Crisis Management. ISCRAM; 2022.
[9] Xu F, Ma J, Li N, Cheng JC. Large language model applications in disaster management: An interdisciplinary review. International Journal of Disaster Risk Reduction. 2025;127:105642.
[10] Hadid A, Chakraborty T, Busby D. When geoscience meets generative AI and large language models: Foundations, trends, and future challenges. Expert Systems. 2024;41(10):e13654.
[11] Estêvão JM. Effectiveness of generative ai for post-earthquake damage assessment. Buildings. 2024;14(10):3255.
[12] Jiang Y, Wang J, Shen X, Dai K. Large language model for post‐earthquake structural damage assessment of buildings. Computer‐Aided Civil and Infrastructure Engineering. 2025;40(31):6324-42.
[13] Cheng Y, Zhao H, Zhou X, Zhao J, Cao Y, Yang C, et al. A large language model for advanced power dispatch. Scientific Reports. 2025;15(1):8925.
[14] Pu H, Yang X, Shi Z, Jin N, editors. Automated inspection report generation using multimodal large language models and set-of-mark prompting. ISARC Proceedings of the International Symposium on Automation and Robotics in Construction; 2024: IAARC Publications.
[15] Zhang R, El-Gohary N. Natural language generation and deep learning for intelligent building codes. Advanced Engineering Informatics. 2022;52:101557.
[16] Lin Y, Ruan T, Liu J, Wang H. A survey on neural data-to-text generation. IEEE Transactions on Knowledge and Data Engineering. 2023;36(4):1431-49.
[17] Sharma M, Gogineni AK, Ramakrishnan N. Neural methods for data-to-text generation. ACM Transactions on Intelligent Systems and Technology. 2024;15(5):1-46.
[18] Devlin J, Chang M-W, Lee K, Toutanova K, editors. Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 conference of the North American Section of the association for computational linguistics: human language technologies, volume 1 (long and short papers); 2019.
[19] Weld H, Huang X, Long S, Poon J, Han SC. A survey of joint intent detection and slot filling models in natural language understanding. ACM Computing Surveys. 2022;55(8):1-38.
[20] Xiao H, Zhou F, Liu X, Liu T, Li Z, Liu X, et al. A comprehensive survey of large language models and multimodal large language models in medicine. Information Fusion. 2025;117:102888.
[21] Dathathri S, Madotto A, Lan J, Hung J, Frank E, Molino P, et al. Plug and play language models: A simple approach to controlled text generation. arXiv preprint arXiv:191202164. 2019.
[22] Geng S, Döner B, Wendler C, Josifoski M, West R, editors. Sketch-guided constrained decoding for boosting blackbox large language models without logit access. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers); 2024.
[23] Park K, Wang J, Berg-Kirkpatrick T, Polikarpova N, D'Antoni L. Grammar-aligned decoding. Advances in Neural Information Processing Systems. 2024;37:24547-68.
[24] Survey USG. ANSS Comprehensive Catalog (ComCat) Earthquake Catalog 2025 [Available from: https://earthquake.usgs.gov/fdsnws/event/1.
[25] She B, Adetola V, Yun JY. Event-correlated Outage Dataset in America. Open Energy Data Initiative (OEDI). Pacific Northwest National Laboratory; 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Kan Shi, Zuoqing Li, Huali Hu, Lei Zhang, Desong Wang, Yifan Han, Xiang Wang
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.
