基于知识图谱的报文故障分析与检索

doi:10.3969/j.issn.0255-8297.2023.03.002

应用科学学报 ›› 2023, Vol. 41 ›› Issue (3): 378-390.doi: 10.3969/j.issn.0255-8297.2023.03.002

基于知识图谱的报文故障分析与检索

嵇文路¹, 邓星¹, 朱红勤¹, 赵杨¹, 江结林²

1. 国网江苏省电力有限公司南京供电分公司, 江苏南京 210019;
2. 南京信息工程大学软件学院, 江苏南京 210044

收稿日期:2022-10-25 出版日期:2023-05-30 发布日期:2023-06-16
通信作者: 江结林,副教授,研究方向为调度自动化、边缘计算、图像复原。E-mail:jiangjielin2008@nuist.edu.cn E-mail:jiangjielin2008@nuist.edu.cn
基金资助:
国家电网有限公司科技项目基金(No. J2021167)资助

Fault Analysis and Retrieval of Message Based on Knowledge Graph

JI Wenlu¹, DENG Xing¹, ZHU Hongqin¹, ZHAO Yang¹, JIANG Jielin²

1. Nanjing Power Supply Company, State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210019, Jiangsu, China;
2. School of Software, Nanjing University of Information Science and Technology, Nanjing 210044, Jiangsu, China

Received:2022-10-25 Online:2023-05-30 Published:2023-06-16

摘要/Abstract

摘要： 针对电网规模扩大带来的故障分析模式复杂、故障排除困难等问题，提出一种基于知识图谱的报文故障分析与检索方法。首先通过自然语言处理技术结合专家文档，完成电力调度故障知识图谱的构建。然后将专家知识以原子规则（不可分割的规则）的形式存储于图谱中，实现智能化故障分析、检索及辅助维护人员决策等目标，从而提高业务过程效率。最后结合知识图谱与日志信息，利用神经网络分析故障成因，从多个潜在解中获取最优解。实验结果表明：在真实数据和合成数据上，该方法能获得很好的故障分析与检索效果。

关键词: 故障分析, 知识图谱, 自然语言处理, 调度自动化

Abstract: Aiming at the problems of complex fault analysis mode and increasing difficulty of fault removal caused by the expansion of the power grid, a fault analysis and retrieval of message based on knowledge graph is proposed. Firstly, the construction of power dispatching fault knowledge graph is completed by combining natural language processing technology with expert documents. Then the expert knowledge is stored in the graph in the form of atomic rules (indivisible rules) to achieve intelligent fault analysis and retrieval and assist maintenance personnel in decision-making, thereby improving the efficiency of business process. Finally, combined with the knowledge graph and log information, artificial intelligence is used to analyze the cause of failure, and the optimal solution is obtained from multiple potential solutions. Experimental results on both real and synthetic data sets show that the proposed method can achieve good results on fault analysis and retrieval in power dispatching.

Key words: fault analysis, knowledge graph, natural language processing, dispatching automation

中图分类号:

P751.1

嵇文路, 邓星, 朱红勤, 赵杨, 江结林. 基于知识图谱的报文故障分析与检索[J]. 应用科学学报, 2023, 41(3): 378-390.

JI Wenlu, DENG Xing, ZHU Hongqin, ZHAO Yang, JIANG Jielin. Fault Analysis and Retrieval of Message Based on Knowledge Graph[J]. Journal of Applied Sciences, 2023, 41(3): 378-390.

参考文献

[1] Jiang Y, Ni Y, Su A, et al. New information interface scheme for substation monitoring information based on e language and IEC104 protocol [C]//2020 Asia Energy and Electrical Engineering Symposium (AEEES), 2020: 678-683.
[2] Wang B, Li F, Chen T, et al. Research on deep analysis technology of real time interaction protocol in power industrial control system [C]//2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), 2021: 75-80.
[3] Paul B B, Orven E L. Design and implementation of real-time mobile-based water temperature monitoring system [J]. Procedia Computer Science, 2017, 124: 698-705.
[4] 毕艳冰, 蒋林, 王新军, 等. 面向服务的智能电网调度控制系统架构方案[J]. 电力系统自动化, 2015, 39(2): 92-99. Bi Y B, Jiang L, Wang X J, et al. Service-oriented architecture scheme for smart grid dispatch control system [J]. Automation of Electric Power Systems, 2015, 39(2): 92-99. (in Chinese)
[5] 程路明, 楼平, 诸骏豪, 等. 基于APRIORI-贝叶斯优化XGBoost的电力通信网根告警预测[J]. 电力建设, 2022, 43(1): 113-121. Cheng L M, Lou P, Zhu J H, et al. Power communication network root alarm prediction based on APRIORI Bayesian optimization XGBoost [J]. Power Construction, 2022, 43(1): 113-121. (in Chinese)
[6] 黄军凯, 张迅, 刘君, 等. 基于IGA-BP混合算法的电力变压器智能故障诊断分析[J]. 信息系统工程, 2021(10): 105-107. Huang J K, Zhang X, Liu J, et al. Intelligent fault diagnosis analysis of power transformer based on IGA-BP hybrid algorithm [J]. Information System Engineering, 2021(10): 105-107. (in Chinese)
[7] 朱燕芳, 闫磊, 常康, 等. 基于深度卷积神经网络的电力系统故障预测[J]. 电源学报, 2022: 1-14. Zhu Y F, Yan L, Chang K, et al. Power system fault prediction based on deep convolution neural network [J]. Journal of Power Supply, 2022: 1-14. (in Chinese)
[8] Yang B, Liao Y. Research on enterprise risk knowledge graph based on multi-source data fusion [J]. Neural Computing and Applications, 2022, 34(4): 2569-2582.
[9] Liu G, Li L. Knowledge fragment cleaning in a genealogy knowledge graph [C]//2020 IEEE International Conference on Knowledge Graph (ICKG), 2020: 521-528.
[10] 曹皓伟, 徐建良, 窦方坤. 基于Neo4j生物医药知识图谱的构建[J]. 计算机时代, 2020, 336(6): 35-38. Cao H W, Xu J L, Dou F K. Construction based on Neo4j biomedical knowledge graph [J]. Computer Age, 2020, 336(6): 35-38. (in Chinese)
[11] Wei T, Jiang Y, Wang Y, et al. Semi-automated construction of a knowledge graph with template [J]. IOP Conference Series Materials Science and Engineering, 2020, 782: 032054.
[12] Zhao Q, Huang H, Ding H. Study on military regulations knowledge construction based on knowledge graph [C]//20217th International Conference on Big Data and Information Analytics (BigDIA), 2021: 180-184.
[13] 阮光册, 樊宇航, 夏磊. 知识图谱在实体检索中的应用研究综述[J]. 图书情报工作, 2020, 64(14): 126-135. Ruan G C, Fan Y H, Xia L. Overview of the application of knowledge atlas in entity retrieval [J]. Library and Information Work, 2020, 64(14): 126-135. (in Chinese)
[14] Wu X, Xiao L, Sun Y, et al. A survey of human-in-the-loop for machine learning [J]. Future Generation Computer Systems, 2022, 135: 364-381.
[15] 唐钰, 唐加山. 一种改进的TF-IDF文本分类算法[J]. 信息技术与信息化, 2022, 3: 13-16. Tang Y, Tang J S. An improved TF-IDF text classification algorithm [J]. Information Technology and Informatization, 2022, 3: 13-16. (in Chinese)
[16] Li X, Deng Q. Chinese position segmentation based on ALBERT-BiGRU-CRF model [C]//2021 International Symposium on Computer Technology and Information Science (ISCTIS), 2021: 116-120.
[17] Sun Q, Jankovic M V, Bally L, et al. Predicting blood glucose with an LSTM and BiLSTM based deep neural network [C]//201814th Symposium on Neural Networks and Applications (NEUREL). IEEE, 2018: 1-5.
[18] Wang Z, Zhang J, Feng J, et al. Knowledge graph embedding by translating on hyperplanes [C]//AAAI Conference on Artificial Intelligence, 2014: 1112-1119.
[19] Fu Z, Xian Y, Zhu Y, et al. HOOPS: human-in-the-loop graph reasoning for conversational recommendation [C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021: 2415-2421.
[20] Kusnerr M, Sun Y, Kolkinl N, et al. From word embeddings to document distances [C]//Proceedings of the 32nd International conference on machine learning, 2015: 957-966.
[21] Jayakodi K, Bandara M, Perera I, et al. WordNet and cosine similarity based classifier of exam questions using bloom’s taxonomy [J]. International Journal of Emerging Technologies in Learning, 2016, 11: 142-149.
[22] Athrey R G, Bansal S K, Ngomo A C N, et al. Template-based question answering using recursive neural networks [C]//IEEE 15th International Conference on Semantic Computing (ICSC). IEEE, 2021: 195-198.
[23] Liu C, Zhang Q, Feng J, et al. A Chinese word segmentation method based on dictionary and HMM [C]//6th International Conference on Electronic Information Technology and Computer Engineering, 2022: 644-649.
[24] Bourlard H, Morgan N. Hybrid HMM/ANN systems for speech recognition: overview and new research directions [J]. International School on Neural Networks, Initiated by IIASS and EMFCSC, 1997: 389-417.
[25] Roy S, Mariappan R, Dandapat S, et al. QART: a system for real-time holistic quality assurance for contact center dialogues [C]//AAAI Conference on Artificial Intelligence, 2016: 3768-3775.
[26] Shao T, Cai F, Chen H, et al. Length-adaptive neural network for answer selection [C]//International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019: 869-872.
[27] Sakata W, Shibata T, Tanaka R, et al. FAQ retrieval using query-question similarity and BERT-based query-answer relevance [C]//International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019: 1113-1116.

基于知识图谱的报文故障分析与检索

Fault Analysis and Retrieval of Message Based on Knowledge Graph

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	刘明辉, 唐望径, 许斌, 仝美涵, 王黎明, 钟琦, 徐剑军. 实体类别信息增强的命名实体识别算法[J]. 应用科学学报, 2023, 41(1): 1-9.
[2]	欧阳志友, 陈晨, 王愉茜, 陈金刚, 殷昭, 周青松. 基于自然语言处理的蛋白质小分子亲和力值预测[J]. 应用科学学报, 2019, 37(3): 327-335.
[3]	张博亮, 钟卫东, 杨晓元. 物联网环境下Feistel结构分组密码的差分故障分析[J]. 应用科学学报, 2016, 34(5): 547-554.
[4]	沈璇, 赵光耀, 李超, 李瑞林. MD5加密模式的差分故障分析[J]. 应用科学学报, 2015, 33(5): 481-490.