摘要
作为国民经济发展的支柱产业,建筑业安全事故频发,施工安全形势严峻。为有效评估和降低建筑施工安全风险,将T-S模糊故障树和贝叶斯网络进行结合,建立一种建筑施工风险评估模型。利用T-S门规则和贝叶斯网络的条件概率,建立T-S模糊故障树的贝叶斯网络转化模型,引入模糊理论对事件风险概率进行模糊化,最终借助贝叶斯网络双向推理算法计算故障概率、重要度及后验概率。结果表明,该模型能够根据基本事件风险概率进行量化计算,以正向推理方式计算体系事故发生概率;能够量化根节点的模糊重要度,确定事件重点管控顺序;且可以通过反向推理计算根节点后验概率,确定故障排查顺序。该计算模型最大限度贴近实际施工情形,更加科学合理地进行建筑施工风险评估,可为建筑施工的安全风险评估和精准化管理提供理论支持。
Safety accidents in the construction industry have occurred frequently. As the mainstay industry in our country, the safety situation of the construction industry is not optimistic. To evaluate and reduce the safety risks of the construction industry effectively, this study establishes a building construction risk assessment model. This model transforms the T-S Fuzzy Fault Tree to Bayesian Network by T-S gate rules and the conditional probability of the Bayesian Network. The event risks can be evaluated by fuzzy theory. The degree of the construction system, fuzzy importance and posterior probability can be calculated by the Bayesian network two-way inference algorithm. The results show that the method proposed in this study can define the system risk level according to the event risks. On the one hand, the fuzzy importance of events can provide help for management. On the other hand, the reverse calculation can verify the root events’ probabilities to clarify the order of risks. Compared with the previous method, this model matches the actual construction situation as much as possible. The advantage of this method is that its assessment results are more scientific and objective. Therefore, this method can provide theoretical support for the safety risk evaluation and targeted control of construction.
作者
杜敏维
于德湖
邵志国
DU Minwei;YU Dehu;SHAO Zhiguo(School of Civil Engineering,Qingdao University of Technology,Qingdao 266525,China;School of Management Engineering,Qingdao University of Technology,Qingdao 266525,China)
出处
《青岛理工大学学报》
CAS
2023年第1期21-29,共9页
Journal of Qingdao University of Technology
基金
山东省重点研发计划(重大科技创新工程)(2021CXGC11204)。
关键词
建筑施工
风险评估
T-S模糊故障树
贝叶斯网络
安全管理
building construction
risk assessment
T-S Fuzzy Fault Tree
Bayesian network
safety management
作者简介
杜敏维(1996-),男,山东烟台人。硕士,研究方向为建筑与土木工程。E-mail:marvindu@qq.com;通信作者:于德湖(1975-),男,黑龙江大兴安岭人。博士,教授,主要从事结构抗震、土木工程信息化方面的研究。E-mail:yudehu@126.com。
