主管：中华人民共和国应急管理部
主办：应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU
消防科学与技术

消防科学与技术 ›› 2024, Vol. 43 ›› Issue (6): 826-830.

• • 上一篇    下一篇

储气库站场天然气泄漏及火灾事故应急知识图谱构建

宋旭1, 文明1, 胡瑾秋2,3, 龚建华4   

  1. （1. 中国石油天然气股份有限公司西南油气田分公司 安全环保与技术监督研究院，四川 成都 610041；2. 中国石油大学（北京） 安全与海洋工程学院，北京 102249；3. 中国石油大学（北京） 油气生产安全与应急技术应急管理部重点实验室，北京 102249；4. 中国石油天然气股份有限公司西南油气田分公司 质量安全环保处，四川 成都 610084）
  • 出版日期:2024-06-15 发布日期:2024-06-15
  • 作者简介:宋 旭（1986- ），中国石油天然气股份有限公司西南油气田分公司安全环保与技术监督研究院工程师，学士，主要从事安全管理方面的研究工作，四川省成都市高新区天府大道北段12号，610041。
  • 基金资助:
    国家自然科学基金资助（52074323）；中国石油集团公司科技课题（2021DJ6505）

Construction of emergency knowledge graph for gas leakage and fire accidents at gas storage facility sites

Song Xu1, Wen Ming1, Hu Jinqiu2,3, Gong Jianhua4   

  1. (1. Safety, Environment & Technology Supervision Research Institute, PetroChina Southwest Oil & Gasfield Company, Sichuan Chengdu 610041, China; 2. College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China; 3. Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, China University of Petroleum (Beijing), Beijing 102249, China; 4. Quality, Safety, and Environmental Protection Department, PetroChina Southwest Oil & Gasfield Company, Sichuan Chengdu 610084, China)
  • Online:2024-06-15 Published:2024-06-15

摘要： 针对消防、应急处置过程中快速进行决策支持和方案制定的难点，提出储气库站场天然气泄漏及火灾事故的应急模型，该模型应用知识图谱作为风险表征手段，利用双向编码表示转换器（BERT）和双向长短时记忆模型条件随机场算法（Bi-LSTM-CRF），实现对文本信息的实体识别和关系抽取。利用Neo4j图数据库构建储气库站场天然气泄漏及火灾事故的应急知识图谱。结果表明：相较于传统的应急处置、消防策略研究方法，本文提出的储气库站场天然气泄漏及火灾事故应急模型不仅可以实现对储气库站场天然气泄漏及火灾事故的早期应急处置，还能够识别事故的风险传播路径，为消防应急指挥和应急决策提供支持。

关键词: 消防救援, 应急决策, 知识图谱, 天然气泄漏, BERT-Bi-LSTM-CRF

Abstract: Aiming at the difficulty of rapid decision support and plan formulation in the firefighting and emergency response process, this article proposes an emergency model for gas leakage and fire accidents at gas storage facility sites. This model uses a knowledge graph as a means of risk characterization, employing Bidirectional Encoder Representations from Transformers (BERT) and Bidirectional Long Short-Term Memory Model Conditional Random Field algorithm (Bi-LSTM-CRF) for entity recognition and relationship extraction from textual intelligence. The emergency knowledge graph for gas leakage and fire accidents at gas storage facility sites is constructed using the Neo4j graph database. The results show that compared to traditional emergency handling and firefighting strategy research methods, the emergency model proposed in this paper for gas leakage and fire accidents at gas storage facility sites not only enables early emergency handling but also identifies the risk propagation paths of accidents, providing support for firefighting emergency command and emergency decision-making.

Key words: firefighting and rescuing, emergency decision, knowledge graph, natural gas leakage, BERT-Bi-LSTM-CRF