2025 Vol.8 Jun.N03

• Title: Knowledge Graph Construction for Transformer Monitoring and Maintenance
• Name: Chen Jie
• Company: Shanghai Lingzhi Internet of Things Co., Ltd., Shanghai 200123 China
• Abstract:

  Aiming at the monitoring and maintenance of transformers in the process of power production and operation, we propose a domain knowledge graph construction method based on a multidimensional domain concept model, which models the information of the whole process of transformer monitoring and operation and maintenance scenarios in three dimensions: physical elements, data features and fault events; extracts entities and relations from domain knowledge and industry documents through natural language processing algorithms, and forms a domain knowledge graph through semantic relations The domain knowledge base is formed through the fusion of natural language processing algorithms, and a locally available transformer monitoring and maintenance knowledge map is constructed. Based on the method research, a power transformer inspection and maintenance knowledge mapping platform is built for the actual maintenance business of a power station to meet the needs of fault location, structure analysis and comprehensive fault analysis for various types of transformers and multiple fault problems. Compared with the traditional transformer knowledge mapping, the knowledge mapping and platform application achieve richer knowledge types, stronger data correlation and better flexibility of scenario application.

• Keyword: transformer; fault monitoring; semantic web; information modeling; knowledge graph
• DOI: 10.12250/jpciams2025090606
• Citation form: Chen Jie.Knowledge Graph Construction for Transformer Monitoring and Maintenance[J]. Computer Informatization and Mechanical System,2025,Vol.8,pp.24-29

References

[1] Gao Jun. Research on fault diagnosis and state comprehensive evaluation of power transformer[J]. Huazhong University of Science and Technology, 2011, 201: 1-05.

[2] Sheng Gehao, Qian Yong, Luo Lingen, et al. Key technologies of power equipment operation and maintenance for new power systems and their application[J]. High Voltage Technology, 2021, 47(9): 3072-3084.

[3] ZHOU Wenchao,ZHOU Zihan,JIN Chong. Research on partial discharge fault diagnosis of transformer based on SVM[J]. Railroad Communication Signal Engineering Technology,2022,19(S1):137-140.

[4] HUANG Lei,WANG Hui. Fault diagnosis of dissolved gas concentration in transformer oil based on convolutional neural network[J]. Electrical Appliance Industry,2023(01):45-50.

[5] Liu Zheng. Research on fault diagnosis of dry-type transformer based on temperature field finite element analysis[D]. Tianjin University of Technology,2019.

[6] Singhal A. Introducing the knowledge graph: things, not strings[J]. Official google blog, 2012, 5(16): 3.

[7] Bao Y, Tang F, Li X, et al. Semantic-Based Heterogeneous Controller Collaboration for Space-Terrestrial Integrated Networks[C]//2021 IEEE 23rd Int. Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2021: 571-578.

[8] Yu H, Cai H, Liu Z, et al. An Automated Metadata Generation Method for Data Lake of Industrial WoT Applications[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 52(8): 5235-5248.

[9] Sha Q, Yang Q, Li G. A Parallel Implementation of Liveness on Knowledge Graphs under Label Constraints[C]//2021 International Symposium on Theoretical Aspects of Software Engineering (TASE). IEEE, 2021: 103-110.

[10] ZHAO Jun, DONG Qinwei, WU Jun, DAI Wei. An algorithm for power engineering knowledge graph architecture based on multi-source heterogeneous data fusion[J]. Electronic Design Engineering,2022,30(23):37-41.DOI:10.14022/j.issn1674-6236.2022.23.009.

[11] Li Xiaoyu. A knowledge graph based fault diagnosis method for power grid [D]. North China Electric Power University (Beijing), 2022.DOI:10.27140/d.cnki.ghbbu.2022.000678.

[12] DONG Li Ke, BAI Heron, WU Na, YANG Dong Dong. Research on fault prediction method of power transformer based on knowledge graph[J]. High Voltage Electrical Apparatus,2022,58(11):151-159.DOI:10.13296/j.1001-1609.hva.2022.11.019.

[13] XIE Qing, CAI Yang, XIE Jun, WANG Chunxin, ZHANG Yutong, XU Zhikang. Research on the construction method and application of ALBERT-based knowledge graph for power transformer operation and maintenance[J]. Journal of Electrotechnology,2023,38(01):95-106.DOI:10.19595/j.cnki.1000-6753.tces.221751.

[14] Huang Z, Xu W, Yu K. Bidirectional LSTM-CRF models for sequence tagging[J]. arXiv preprint arXiv:1508.01991, 2015.

[15] Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018.