| 城市燃气管网泄漏事故分析知识图谱构建及应用研究* |
| |
| 引用本文： | 李聪,徐子烜,王雨情,许文博,杨锐.城市燃气管网泄漏事故分析知识图谱构建及应用研究*[J].中国安全生产科学技术,2022,18(10):5-12. |
| |
| 作者姓名： | 李聪 徐子烜 王雨情 许文博 杨锐 |
| |
| 作者单位： | （1.中国矿业大学（北京） 应急管理与安全工程学院，北京 100083；2.清华大学 工程物理系公共安全研究院，北京 100084） |
| |
| 基金项目： | * 基金项目: 国家重点研发计划项目（2021YFF0600403）；国家自然科学基金项目（U2033206）；中央高校基本科研业务经费项目（2022YQAQ05） |
| |
| 摘 要： | 为深入认识燃气管网泄漏事故的发生发展机理，提高事故分析预测的自动化、智能化、数字化水平，利用知识图谱对燃气管网泄漏事故进行研究。在事故案例分析的基础上，从人-物-环-管的角度对燃气泄漏过程以及火灾爆炸次生事故的相关实体进行归纳梳理，对实体间的逻辑关系和非逻辑关系进行辨识，并对实体的属性进行分类，进而构建出较为全面的燃气管网泄漏事故知识图谱。在此基础上，搭建BP神经网络模型，基于已知实体或属性状态，预测相关联其他实体或属性的状态。研究结果表明:燃气管网知识图谱能够有效展示燃气管网泄漏事故发展的动态过程及相关要素，结合BP神经网络能够有效预测事故的发展路径及相关状态，从而提高燃气管网泄漏事故的分析预测水平与效率。
|
| 关 键 词： | 燃气管网 燃气泄漏 知识图谱 模式层 神经网络 |
Construction and application of knowledge graph for leakage accident analysis of urban gas pipeline network |
| |
| LI Cong,XU Zixuan,WANG Yuqing,XU Wenbo,YANG Rui.Construction and application of knowledge graph for leakage accident analysis of urban gas pipeline network[J].Journal of Safety Science and Technology,2022,18(10):5-12. |
| |
| Authors: | LI Cong XU Zixuan WANG Yuqing XU Wenbo YANG Rui |
| |
| Affiliation: | (1.School of Emergency Management and Safety Engineering,China University of Mining and Technology (Beijing),Beijing 100083,China;2.Institute of Public Safety Research,Department of Engineering Physics,Tsinghua University,Beijing 100084,China) |
| |
| Abstract: | In order to fully understand the occurrence and development mechanism of the leakage accident of gas network,and improve the automation,intelligence and digitalization level of accident analysis and prediction,the leakage accident of gas pipeline network were studied by using the knowledge graph.On the basis of accident cases analysis,the related entities of gas leakage process and secondary accidents of fire and explosion were summarized from the perspective of man-material-environment-management.The logical and non-logical relationship between the entities were identified,and then the attributes of entities were classified to construct a more comprehensive knowledge graph of gas pipeline network leakage accidents.Based on this,a BP neural network model was constructed to predict the state of related other entities or attributes based on the known entity or attribute state.The results showed that the knowledge graph of gas pipeline network could effectively demonstrate the dynamic process and relevant elements of the development of gas pipeline network leakage accidents,and the combination of BP neural network could effectively predict the development path and relevant states of the accidents,thus improving the analysis and prediction level and efficiency of gas pipeline network leakage accidents. |
| |
| Keywords: | gas pipeline network gas leakage knowledge graph schema-level neural network |
|
| 点击此处可从《中国安全生产科学技术》浏览原始摘要信息 |
|
点击此处可从《中国安全生产科学技术》下载全文 |
