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 ›› 2026, Vol. 45 ›› Issue (9): 81-89.

• • 上一篇    下一篇

基于BERT-BN的商业场所火灾风险评估方法

王敏1, 马春晨2, 杨明星2, 季经纬1, 张藤镨1   

  1. (1.中国矿业大学 安全工程学院,江苏 徐州 221116; 2.深圳高速运营发展有限公司,广东 深圳 518000)
  • 收稿日期:2025-07-31 修回日期:2025-11-03 出版日期:2026-09-15 发布日期:2026-09-15
  • 作者简介:王敏,中国矿业大学硕士研究生,主要从事火灾风险评估方面的研究,江苏省徐州市铜山区大学路1号,221116,18764271701@163.com。

BERT-BN integrated approach for fire risk assessment in commercial premises

Wang Min1, Ma Chunchen2, Yang Mingxing2, Ji Jingwei1, Zhang Tengpu1   

  1. (1. School of Safety Engineering, China University of Mining and Technology, Xuzhou Jiangsu 221116, China;2. Shenzhen Expressway Operation & Development Co., Ltd., Shenzhen Guangdong 518000, China)
  • Received:2025-07-31 Revised:2025-11-03 Online:2026-09-15 Published:2026-09-15

摘要: 为提升商业场所传统火灾风险评估方法的准确性与效率,本文提出一种基于BERT算法与贝叶斯网络(BN)的火灾风险评估方法。通过分析火灾事故报告和专家评估报告,构建适用于各类商业场所的火灾风险指标体系。利用BERT算法构建指标自动生成模型,实现与商业场所特征相匹配的火灾风险指标的自动生成。在指标生成基础上,结合贝叶斯网络对商业场所火灾风险进行量化计算。以某大型商业综合体为例,通过自动生成模型获取匹配指标,并运用贝叶斯网络计算各指标节点的概率分布及整体火灾风险,验证了该方法的可行性。

关键词: 商业建筑, 火灾风险, BERT算法, 贝叶斯网络, 指标体系

Abstract: To improve the accuracy and efficiency of traditional fire risk assessment methods for commercial premises, this paper proposes a fire risk assessment method based on the combination of the BERT algorithm and Bayesian Network (BN). By analyzing fire accident reports and expert assessment reports, a fire risk indicator system applicable to various types of commercial premises is established. The BERT algorithm is utilized to construct an automatic indicator generation model, enabling the automatic generation of fire risk indicators that match the characteristics of commercial premises. Based on the generated indicators, the Bayesian Network is employed to calculate the fire risk of commercial premises. Taking a large commercial complex as a case study, the matching indicators are obtained through the automatic generation model, and the Bayesian Network is used to calculate the probability distribution of each indicator node and the overall fire risk, thereby verifying the feasibility of the proposed method.

Key words: commercial buildings, fire risk, BERT algorithm, Bayesian Networks, indicator system