Author(s)

Yuan Zhang^*, Chao Si, YanKun Li

Affiliation(s)

Electrical Department, China Institute of Atomic Energy, Beijing 102400, China.

Corresponding Author

Yuan Zhang

ABSTRACT

Traditional knowledge management in nuclear reactor operation and maintenance (O&M) relies on dispersed documents and individual expertise, limiting knowledge reuse and response efficiency. This paper introduces a knowledge-graph-driven intelligent question answering (QA) system that constructs a unified semantic representation of equipment, faults, and procedures through structured entity extraction, relationship modeling, and rule-based reasoning. Neo4j serves as the graph database, while the Dijkstra shortest path algorithm supports association path computation for fault cause inference and similar-case retrieval. The system integrates with a digital O&M platform for real-time data acquisition and structuring. Simulation-based validation in a reactor refueling system scenario demonstrates that the system shows promising potential in the following aspects: enhancing standardization and traceability of fault information, reducing fault diagnosis and handling time, and providing reliable data support for team capability evaluation and equipment health assessment. This work provides a scalable framework for knowledge management in complex industrial systems, contributing to improved O&M efficiency and safety in nuclear operations.

KEYWORDS

Knowledge graph; Intelligent question answering; Nuclear reactor operation and maintenance; Fault diagnosis; Knowledge reasoning

CITE THIS PAPER

Yuan Zhang, Chao Si, YanKun Li. Design and application of a Knowledge-Graph-Based Intelligent question answering system for reactor operation and maintenance. World Journal of Information Technology. 2025, 3(5): 68-82. DOI: https://doi.org/10.61784/wjit3069.

REFERENCES

[1] Ji S, Pan S, Cambria E, et al. A survey on knowledge graphs: Representation, acquisition and applications. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(2): 494-514.

[2] Chen J, Zhang H, Wang H. Knowledge graph and its application in intelligent question answering: A survey. In: 2020 IEEE International Conference on Big Data (Big Data), 2020: 2273-2282.

[3] Paulheim H. Knowledge graph refinement: A survey of approaches and evaluation methods. Semantic Web, 2017, 8(3): 489-508.

[4] Wang X, Pan W, Gao X. Application of knowledge graph technology in power equipment operation and maintenance. In: 2021 IEEE International Conference on Power System Technology (POWERCON), 2021: 338-344.

[5] Zhang CY. Research and implementation of automatic question answering system based on knowledge graph. Beijing University of Posts and Telecommunications, 2018.

[6] Xiong W, Yu M, Chang S, et al. One-shot relational learning for knowledge graphs. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2018: 1980-1990.

[7] Robinson I, Webber J, Eifrem E. Graph Databases. 2nd ed. O’Reilly Media, 2015.

[8] Miller JJ. Graph database applications and concepts with Neo4j. In: Proceedings of the Southern Association for Information Systems Conference, 2013: 1-6.

[9] Malewicz G, Austern MH, Bik AJ, et al. Pregel: A system for large-scale graph processing. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data, 2010: 135-146.

[10] Low Y, Bickson D, Gonzalez J, et al. Distributed GraphLab: A framework for machine learning and data mining in the cloud. VLDB Endowment, 2012, 5(8): 716-727.

[11] Kyrola A, Belli L, Guestrin C. GraphChi: Large-scale graph computation on just a PC. In: 10th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2012: 31-46.

[12] Shao B, Wang H, Li Y. Trinity: A distributed graph engine on a memory cloud. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, 2013: 505-516.

[13] Sarwat M, Elnikety S, He Y, et al. Horton: An online query execution engine for large distributed graphs. In: 2012 IEEE 28th International Conference on Data Engineering (ICDE), 2012: 1289-1292.

[14] Zhang F, Liu J, Li Q. A shortest path optimization algorithm based on Dijkstra. Remote Sensing Information, 2004(2): 4-7.

[15] Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space. In: International Conference on Learning Representations (ICLR), 2013.