摘要
隧道施工坍塌具有十分复杂的原因,到目前为止仍缺乏成熟可靠的隧道施工坍塌事故诊断方法.在对隧道隧道施工坍塌模式进行分类总结的基础上,引入基于贝叶斯网络的知识表达和不确定性推理,构建了隧道隧道施工坍塌事故诊断的贝叶斯网络模型,基于专家的先验知识构建贝叶斯网络结构,利用NETICA软件的案例学习功能对统计数据进行分析,获得节点间的条件概率,从而建立完整的隧道施工坍塌事故分析专家系统.运用专家系统对某隧道工程施工坍塌事故原因进行分析,专家系统的诊断结果与现场鉴定的结果具有良好的吻合性;贝叶斯网络专家系统可以使推理在输入数据不完备的基础上进行,不仅可以应用于隧道施工坍塌事故分析,同样也可应用于隧道施工支护参数的比选.
The reasons for tunnel collapse accidents are very complicated, which leads to the lack of reliable ac- cident diagnosis methods so far. Based on the classification of the failure modes , Bayesian network and corre- sponding uncertainty reasoning principle are introduced to develop an expert system for diagnosis of tunnel col- lapse accidents. By combining prior knowledge of domain experts with worksite data recorder, we get the posteri- or probability density of most nodes. The field practices prove that the expert system has good applicability. The Bayesian network based expert system can not only be applied to diagnosis of the tunnel collapse accidents acci- dent, but also be applied making comparison and choice of tunnel support parameters.
出处
《昆明理工大学学报（自然科学版）》
CAS
北大核心
2013年第1期37-44,共8页
Journal of Kunming University of Science and Technology(Natural Science)
基金
国家自然科学基金(71262028)
教育部人文社科基金(12YJC630244)
关键词
贝叶斯网络
施工坍塌
支护参数
专家系统
隧道
Bayesian Network
collapse accident
support parameters
expert system
tunnel
