Research on Knowledge Graph Construction of Nuclear Power Equipment Quality Control with Value Chain Collaboration

doi:10.3901/JME.2025.13.174

Abstract

Abstract: To address the issues of information isolation, lack of connectivity, and data loss and deficiency during the flow of information between organizations and platforms in the value chain of nuclear power equipment, the quality control requirements of the nuclear power equipment value chain are analyzed. The knowledge graph, whose construction and application are further explored, introduced to organize the knowledge embedded in quality texts, facilitating sharing and reusing, to support collaborative quality control. Firstly, a multi-stage hierarchical ontology model across time and space is designed based on an analysis of characteristics of quality texts in the nuclear power equipment value chain. Secondly, an improved few-shot-learning-based entity recognition model and a relative position-based entity relationship matching method are proposed, and then knowledge triples are extracted to construct the knowledge graph. Thirdly, through comprehensive scenario analysis and expert interviews, a set of question-and-answer templates for user interaction with the knowledge graph is designed, a frame based on Retrieval Augmented Generation is defined, and an application for questions and answers aiming at collaborative quality control in the nuclear power equipment value chain is developed. Finally, the effectiveness and superiority of the above methods are validated by comparing with the large language models ChatGPT and keyword matching model. The improved entity recognition model demonstrates better performance in handling smaller quality texts. And the nuclear power equipment quality control with value chain collaboration can be effectively supported through user interaction with the knowledge graph, which contributes positively to the improvement of management levels and efficiency.

Key words: value chain collaboration, quality control, knowledge graph, meta-learning

CLC Number:

TP391
TH166

YANG Jiaxing, WEN Peihan, HU Yaping. Research on Knowledge Graph Construction of Nuclear Power Equipment Quality Control with Value Chain Collaboration[J]. Journal of Mechanical Engineering, 2025, 61(13): 174-191.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.cjmenet.com.cn/EN/10.3901/JME.2025.13.174

http://www.cjmenet.com.cn/EN/Y2025/V61/I13/174

References

[1] 胡炳涛，冯毅雄，密尚华，等. 面向核电装备的全生命周期价值链协同模式研究[J]. 机械工程学报，2022，58(13)：213-227. HU Bingtao，FENG Yixiong，MI Shanghua，et al. Novel collaborative mode of lifecycle value chain for nuclear power equipment[J]. Journal of Mechanical Engineering， 2022，58(13)：213-227.
[2] ELBAYOUMI A，TAHVONEN T. Novel methodology for functional design chain analysis of a nuclear power plant：A new built Finnish power plant case study[J]. Nuclear Engineering and Design，2022，393：111795.
[3] YANG Guang，HUANG Wenjie. An analysis of china's nuclear power plant programme supply chain from the perspective of Life Cycle[C]//Environmental Science and Information Application Technology，IEEE Computer Society，2009，3：629-632.
[4] ADAIL A S，AMMAR Y M，ELBASET A A，et al. Analytical study and real simulation for improving the safety of ageing nuclear facility using UPFC[J]. Scientific Reports，2024，14(1)：210.
[5] GAO Jiarong，LIU Yongkuo，DUAN Chengjie，et al. Research on fault diagnosis of electric gate valve in nuclear power plant based on the VMD-MDI-ISSA-RF model[J]. Annals of Nuclear Energy，2024，207：110701.
[6] MA Zhanguo，DENG Shiguang，ZHOU Zhuoran，et al. Expert knowledge modelling software design based on signed directed graph with the application for PWR fault diagnosis[J]. Annals of Nuclear Energy，2024，196：110206.
[7] XU Mengyu，YI Shuping，SI Hengyuan，et al. Assessing the collaborative quality value in nuclear power intelligent construction：A value chain analysis method based on double-layer GERT network[J]. Nuclear Engineering and Design，2024，418：112933.
[8] ZHAO Zetian，HU Bingtao，FENG Yixiong，et al. Evolution game model and simulation analysis of value chain cross-enterprise quality supervision for nuclear power equipment[C]//2022 IEEE 31st International Symposium on Industrial Electronics (ISIE)，IEEE，2022：786-791.
[9] 徐梦宇，易茜，单玉忠，等. 基于系统动力流图的核电装备智能制造协同质量价值建模[J]. 机械工程学报，2022，58(12)：270-282. XU Mengyu，YI Qian，SHAN Yuzhong，et al.Collaborative quality value modeling for intelligent manufacturing of nuclear power equipment based on system dynamic flow diagram[J]. Journal of Mechanical Engineering，2022，58(12)：270-282.
[10] 冯毅雄，赵泽田，胡炳涛，等. 核电装备全生命周期价值链协同平台研究[J]. 计算机集成制造系统，2022，28(9)：2633-2649. FENG Yixiong，ZHAO Zetian，HU Bingtao，et al. Collaborativeplatform of lifecycle value chain fornuclearpower equipment[J]. Computer Integrated Manufacturing Systems，2022，28(9)：2633-2649.
[11] WEN Peihan，ZHENG Li，YI Shuping. Object recognition-based automated inspection system for hose assembly[J]. Proceedings of the Institution of Mechanical Engineers Part B Journal of Engineering Manufacture，2015，229(Suppl)：27-42.
[12] MPLINARI M，NARCISI V，CIURLUINI C，et al. Transient analysis of OSU-MASLWR with RELAP5[C]// Journal of Physics：Conference Series. IOP Publishing，2022，2177(1)：012018.
[13] SONG Houde，LIU Xiaojing，SONG Meiqi. Comparative study of data-driven and model-driven approaches in prediction of nuclear power plants operating parameters[J]. Applied Energy，2023，341：121077.
[14] PEI Yiru，WU Yichun，WANG Fanyu，et al. Safety analysis of signal quality bits in nuclear power plant distributed control systems based on system-theoretic process analysis method[J]. Process Safety and Environmental Protection，2022，164：219-227.
[15] 冯毅雄，赵泽田，胡炳涛，等. 工业大数据驱动的核电装备智能设计-制造-服务技术与应用[J]. 中国科学：技术科学，2023，53(7)：1043-106. FENG Yixiong，ZHAO Zetian，HU Bingtao，et al. Technology and application of industrial big data-driven intelligent design manufacturing and service for nuclear power equipment[J]. Scientia Sinica(Technologica)，2023，53(7)：1043-1061.
[16] LIN Weiqing，MIAO Xiren，CHEN Jing，et al. Fault detection and isolation for multi-type sensors in nuclear power plants via a knowledge-guided spatial-temporal model[J]. Knowledge-Based Systems，2024，300：112182.
[17] PARK C，HEO W. Review of the changing electricity industry value chain in the ICT convergence era[J]. Journal of Cleaner Production，2020，258：120743.
[18] LI Siqi，WANG Junfeng，RONG Jin. Combining improved DFMEA with knowledge graph for component risk analysis of complex products[J]. Reliability Engineering & System Safety，2024，251：110340.
[19] WEN Peihan，MA Yan，WANG Ruiquan. Systematic knowledge modeling and extraction methods for manufacturing process planning based on knowledge graph[J]. Advanced Engineering Informatics，2023，58：102172.
[20] XU Zhaoguang ，& DANG Yanzhong. Data-driven causal knowledge graph construction for root cause analysis in quality problem solving[J]. International Journal of Production Research，2023，61(10)：3227-3245.
[21] ZHOU Bin，HUA Bao，GU Xinghai，et al. An end-to-end tabular information-oriented causality event evolutionary knowledge graph for manufacturing documents[J]. Advanced Engineering Informatics，2021，50：101441.
[22] ZHAO Yunfei，SMIDTS S. A method for systematically developing the knowledge base of reactor operators in nuclear power plants to support cognitive modeling of operator performance[J]. Reliability Engineering & System Safety，2019，186：64-77.
[23] WANG Yanying，CHENG Ying，QI Qinglin，et al. IDS-KG：An industrial dataspace-based knowledge graph construction approach for smart maintenance[J]. Journal of Industrial Information Integration，2024，38：100566.
[24] HUANG Feiyue，CHENG Lianglun. Distant supervision knowledge extraction and knowledge graph construction method for supply chain management domain[J]. Autonomous Intelligent Systems，2024，4(1)：1-13.
[25] WEN Peihan，FENG Linhan，ZHANG Tian. A hybrid Chinese word segmentation model for quality management-related texts based on transfer learning[J]. PLoS One，2022，17(10)：0270154.
[26] JOHANSSON P，CHAKHUNASHVILI A，BARONE S，et al. Variation mode and effect analysis: a practical tool for quality improvement[J]. Quality and Reliability Engineering International，2006，22(8)：865-876.
[27] LIU Liping，ZHU Fang，CHEN Jie，et al. A quality control method for complex product selective assembly processes[J]. International Journal of Production Research，2013，51：5437-5449.
[28] ZHANG Qiang，LU Xiaonong，PENG Zhanglin，et al. Perspective：A review of lifecycle management research on complex products in smart-connected environments[J]. International Journal of Production Research，2019，57(21)：6758-6779.
[29] MA Qiuping，LI Hongyan，THORSTENSON A. A big data-driven root cause analysis system: Application of Machine Learning in quality problem solving[J]. Computers and Industrial Engineering. 2021，160：107580.
[30] GUIZZARDI G，HALPIN T，et al. Ontological foundations for conceptual modelling[J]. Applied Ontology，2008，3(1-2)：1-12.
[31] WEN Peihan，ZHAO Yiming，LIU Jin. A systematic knowledge graph-based smart management method for operations: A case study of standardized management[J]. Heliyon，2023，9(10)：e20390.
[32] XU Jing，ZHOU Lei，CHEN Pinglu，et al. Whole lifecycle evolution control method of modular product structure oriented to personalized service[J]. International Journal of Computer Integrated Manufacturing，2021，34(10)：1108-1124.
[33] DEVLIN J，CHANG M，LEE K，et al. BERT：pre-training of deep bidirectional transformers for language understanding[C]//North American Chapter of the Association for Computational Linguistics，2019：4171-4186.
[34] CHEN Xuanang，HE Ben，HUI Kai，et al. Dealing with textual noise for robust and effective BERT re-ranking[J]. Information Processing and Management，2023，60(1)：103135.
[35] 李凡长，刘洋，吴鹏翔，等. 元学习研究综述[J]. 计算机学报，2021，44(2)：422-446. LI Fanzhang，LIU Yang，WU Pengxiang，et al. A survey on recent advances in meta-learning[J]. Chinese Journal of Computers，2021，44(2)：422-446.
[36] FINN C，CHELSEA，ABBEEL P，et al. Model-agnostic meta-learning for fast adaptation of deep networks. International conference on machine learning[C]//Proceedings of Machine Learning Research，PMLR，2017：1126-1135.
[37] SCHMIDHUBER J. Evolutionary principles in self- referentiallearning. on learning now to learn：the meta-meta-meta...-hook[D]. Germany：Technische Universitat Munchen，1987.
[38] LI Shen，ZHAO Zhe，HU Renfen，et al. Analogical reasoning on chinese morphological and semantic relations[C]//Association for Computational Linguistics， 2018：138–143.
[39] RAVI S，LAROCHELLE H. Optimization as a model for few-shot learning[C]//Proceedings of ICLR，2016.
[40] ZHONG Zexuan，CHEN Danqi. A frustratingly easy approach for entity and relation extraction[C]// Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies，2021：50-61.
[41] VASWANI A，SHAZEER N M，PARMAR N，et al. Attention is all you need[C]//Neural Information Processing Systems，2017.
[42] SHAW P，USZKOREIT J，VASWANI A. Self-attention with relative position representations[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies，Volume 2(Short Papers)，2018：464–468.
[43] AHO A V，CORASICK M J. Efficient string matching：an aid to bibliographic search[J]. Communications of the ACM，1975，18(6)：333-340.
[44] KELVIN X，JIMMY B，KIROS R，et al. Show, attend and tell：Neural image caption generation with visual attention[C]//32nd International Conference on Machine Learning，2015，37：2048-2057.
[45] PATRICK S H L，ETHAN P，ALEKSANDRA P，et al. Retrieval-augmented generation for knowledge-intensive NLP tasks[J]. Advances in Neural Information Processing Systems，2020，33：9459-9474.
[46] XU Liang，LU，LIU Minglu，et al. Nanjing Yunjin intelligent question-answering system based on knowledge graphs and retrieval augmented generation technology[J]. Heritage Science，2024，12(1)：118.
[47] KIM Y. Convolutional neural networks for sentence classification[C]//2014 Conference on Empirical Methods in Natural Language Processing，EMNLP，2014：1746-1751.
[48] LIU Pengfei，QIU Xipeng，HUANG Xuanjing. Recurrent neural network for text classification with multi-task learning[J]. Computing Research Repository，2016：2873-2879.
[49] LAI Siwei，XU Liheng，LIU Kang，et al. Recurrent convolutional neural networks for text classification[C]// AAAI Conference on Artificial Intelligence，2015：29(1)：16756501.
[50] SUN Yu，WANG Shuohuan，LI Yukun，et al. ERNIE： enhanced representation through knowledge integration[J]. Computing Research Repository，2019，arXiv：09223.
[51] ZHOU Bin，LI Xinyu，LIU Tianyang，et al. CausalKGPT: industrial structure causal knowledge-enhanced large language model for cause analysis of quality problems in aerospace product manufacturing[J]. Advanced Engineering Informatics，2024，59：102333.
[52] MA Zuyang，YAN Kaihong，WANG Hongwei. BERT-based question answering using knowledge graph embeddings in nuclear power domain[C]//202326th International Conference on Computer Supported Cooperative Work in Design (CSCWD). IEEE，2023：267-272.
[53] HE Zhe，BHASURAN B，JIN Qiao， et al. Quality of answers of generative large language models versus peer users for interpreting laboratory test results for lay patients：evaluation study[J]. Journal of Medical Internet Research，2024，26：56655.
[54] LIU Peifeng，LU Qian，ZHAO Xingwei，et al. Joint knowledge graph and large language model for fault diagnosis and its application in aviation assembly[J]. IEEE Transactions on Industrial Informatics，2024，20：8160-8169.
[55] ZHANG Tianyi，KISHORE V，WU F，et al. Bertscore：Evaluating text generation with bert[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics，2019：1441-1451.