Construction and Optimization of Knowledge Base for Commissioning Plans of New Power System Devices
DOI:
https://doi.org/10.4108/ew.11269Keywords:
Commissioning plans, Power system devices, Knowledge graph, Named entity recognition, Data fusion, Reliability analysisAbstract
To address the challenge of efficiently commissioning new equipment amid grid expansion, this study proposes an intelligent start-up plan generation method based on knowledge graphs. The approach first employs a bidirectional Long Short-Term Memory-Conditional Random Field model to extract entities such as equipment and operations from historical plans. This extraction process enables the construction of a structured knowledge base. Subsequently, it enhances plan standardization and reliability through multi-source data fusion and credibility analysis optimization logic. The results show that the named entity recognition model used in the study achieves an F1 score of 0.99, with an entity recognition accuracy of 92.5% for knowledge related to new power system devices commissioning plans. Testing of the proposed knowledge base reveals a knowledge coverage rate of 93.8%, which is 10.4% higher than that of traditional methods. The efficiency of plan generation significantly improves, with a rule compliance rate reaching 97%. The study provides a feasible pathway for transforming grid startup procedures from reliance on manual experience to data-driven intelligence.
Downloads
References
[1] Zhang Z, Zheng J, Chen Z, et al. (2023) Power grid equipment operation status monitoring system based on Internet of Things technology. ISAEECE 12704:12-17. https://doi.org/10.1117/12.2680429
[2] Zhang Y, Zhong Y, Luo X, et al. (2023) Power equipment fault entity recognition based on BERT-CRF model. AICS 2023 12803:934-941. https://doi.org/10.1117/12.3009433
[3] Zhao S, Zhao H. (2024) Intelligent Power Equipment for Autonomous Situational Awareness and Active Operation and Maintenance. J Mod Power Syst Clean Energy 12:2081-2090. https://doi.org/10.35833/MPCE.2023.000697
[4] Qin W, Guo W, Lin J, et al. (2024) Design and implementation of terminal power information collection and control system based on low-code platform. New J Phys 2903:012009. https://doi.org/10.1088/1742-6596/2903/1/012009
[5] Nallainathan S, Arefi A, Lund C, et al. (2025) Microgrid Reliability Incorporating Uncertainty in Weather and Equipment Failure. Energies 18:2077-2099. https://doi.org/10.3390/en18082077
[6] Weßbecher M, Marianczuk J, Wiegel F, et al. (2023) Management strategies for an ep device in an energy packet grid. EI.A. Springer 14468:240-256. https://doi.org/10.1007/978-3-031-48652-4_16
[7] Feng X, Han J, Liu Y, et al (2024). Dual-Scale Dataset-Based Intelligent Recognition of Power Equipment for Enhanced Digital Grid Planning. TRAIT SIGNAL. 41:919-927. https://doi.org/10.18280/ts.410232
[8] Liu M, Du M, Mu W (2025). Power Grid Engineering Knowledge Graph and Physical Elements Alignment Algorithm Designs. ADS, 2025, 12(6):2009-2039. https://doi.org/10.1007/s40745-025-00650-8
[9] Avdeeva ZK, Gavrilov MS, Lemtyuzhnikova DV, et al. (2024) Methods for solving the problem of topic segmentation of texts based on knowledge graphs. J Comput Syst Sci Int+ 63:642-662. https://doi.org/10.1134/S1064230724700473
[10] Kabal O, Harzallah M, Guillet F, et al. (2024) Enhancing Domain-Independent Knowledge Graph Construction through OpenIE Cleaning and LLMs Validation. Procedia Comput Sci 246:2617-2626. https://doi.org/10.1016/j.procs.2024.09.436
[11] Ivanovski A, Jovanovik M, Stojanov R, et al. (2023) Knowledge Graph Based Recommender for Automatic Playlist Continuation. Information 14:510-522. https://doi.org/10.3390/info14090510
[12] Pu T, Tan Y, Ma Z, et al (2025). Graph Computing Based Knowledge Reasoning in Electric Power System Considering Knowledge Graph Sparsity. CSEE J POWER ENERGY, 11: 2083-2093. https://doi.org/10.17775/CSEEJPES.2022.04120
[13] Santos A, Colaço AR, Nielsen AB, et al. (2022) A knowledge graph to interpret clinical proteomics data. Nat Biotechnol 40:692-702. https://doi.org/10.1038/s41587-021-01145-6
[14] Dutta B, Sarma SK, Talukdar K. (2025) Named Entity Recognition in Assamese Language using two separate models: BiLSTM and BERT. Procedia Comput Sci 258:242-251. https://doi.org/10.1016/j.procs.2025.04.262
[15] Narzary S, Brahma A, Nandi S, et al. (2024) Deep Learning based Named Entity Recognition for the Bodo Language. Procedia Comput Sci 235:2405-2421. https://doi.org/10.1016/j.procs.2024.04.228
[16] Chabalala S, Owolawi P, Ojo S. (2024) CNN to BiLSTM: Enhancing Setswana Named Entity Recognition. WorldComp 2024. Springer 2253:89-104. https://doi.org/10.1007/978-3-031-85856-7_8
[17] Albahadili AJS, Akbas A, Rahebi J. (2024) Detection of phishing URLs with deep learning based on GAN-CNN-LSTM network and swarm intelligence algorithms. Signal Image Video Process 18:4979-4995. https://doi.org/10.1007/s11760-024-03204-2
[18] Yuan Y, Liu X, Lu K. (2024) Multi-Perspective Data Fusion Framework Based on Hierarchical BERT: Provide Visual Predictions of Business Processes. Comput Mater Contin 78:1227-1252. https://doi.org/10.32604/cmc.2023.046937
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yaopu Zheng, Xiongfeng Lin, Shifeng Peng, Guangyu Deng, Yunsheng Huang, Jian Huang
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.
