• 中国科学引文数据库(CSCD)来源期刊
  • 中文核心期刊中文科技核心期刊
  • Scopus RCCSE中国核心学术期刊
  • 美国EBSCO数据库 俄罗斯《文摘杂志》
  • 《日本科学技术振兴机构数据库(中国)》
二维码

隧道建设(中英文) ›› 2023, Vol. 43 ›› Issue (1): 27-35.DOI: 10.3973/j.issn.2096-4498.2023.01.003

• 研究与探索 • 上一篇    下一篇

基于TAN网络的地铁区间与车站施工事故致因分析

申建红12, 刘树鹏1 *   

  1. 1. 青岛理工大学管理工程学院, 山东 青岛 2665202. 青岛理工大学城乡建设信用与风险管理研究中心, 山东 青岛 266520
  • 出版日期:2023-01-20 发布日期:2023-02-16
  • 作者简介:申建红(1970—),男,山东青岛人,2010年毕业于上海大学,结构工程专业,博士,教授,主要从事风险管理、隧道工程质量与安全科研工作。E-mail: sjhqwr@163.com。*通信作者: 刘树鹏, E-mail: liushupeng99@163.com。

Analysis of Causes Related to Construction Accidents in Metro Tunnel and Station Based on Tree Augmented Naive Bayesian

SHEN Jianhong1, 2, LIU Shupeng1, *   

  1. (1.School of Management Engineering,Qingdao University of Technology,Qingdao 266520,Shandong,China;2.Research Institute of Construction Credit and Risk Management,Qingdao University of Technology,Qingdao 266520,Shandong,China)
  • Online:2023-01-20 Published:2023-02-16

摘要: 为解决不同类型的地铁施工事故关键致因识别,以便于支持事故相关方在风险分析、预防和控制进行决策的问题。在收集国内20112021年间发生的202起事故报告数据的基础上,采用树增强朴素贝叶斯(tree augmented naive, TAN)和EM算法,从事故经过、直接原因、间接原因3个角度分别对事故报告进行统计处理、风险指标提取及合并、风险指标筛选、模型图形结构构建、模型参数确定,并采用GENIE软件训练数据建立最终分析模型。贝叶斯模型分析结果表明: 1)通过正向推理明确不同类型事故的关键致险因素,并对各风险因素引发事故的总体影响程度进行重要度排序; 2)通过反向诊断说明所建模型在不同风险因素组合情境下对风险预测的决策支持作用; 310折交叉验证证实了模型的有效性。

关键词: 地铁区间, 车站施工, 安全事故, 树增强朴素贝叶斯(TAN), 致险因素

Abstract: To identify the critical causes of various metro construction accidents and to support the decisionmaking of the accidentrelated parties in risk analysis, prevention, and control, the reported data from 202 metro accidents from 2011 to 2021 in China is collected and statistically processed. The risk indicators are extracted, integrated, and screened. A graphical model structure is constructed and model parameters are determined by tree augmented naive Bayesian and expectationmaximization algorithms, respectively, while considering the perspectives of accident occurrence, direct causes, and indirect causes. The final analysis model is established by training with GENIE software. The analytical results of the Bayesian model reveal the following. First, the essential riskcausing factors for various types of accidents are clarified through forward reasoning, and the overall degree of impact for each risk factor triggering accidents is ranked in importance. Second, the reverse diagnosis illustrates the role of the proposed model in supporting decisionmaking for risk prediction under various risk factor combinations. Third, the 10fold crossvalidation confirms the validity of the model.

Key words: metro section, station construction, safety accident; tree augmented naive Bayesian, risk factors