摘要
为提高公路隧道整体安全性能,保障人员安全,减少财产损失,避免公路隧道水害事故的发生,将Bayes判别理论应用于公路隧道水害倾向性判别和分级中。采用影响隧道水害发生的隧道区渗透系数、降水情况、单位涌水量、构造断裂带类型、围岩分级、隧道施工情况、防排水措施情况等7项指标作为基本判别因子;将公路隧道水害倾向性分为4个等级作为Bayes判别分析的4个正态总体。以采自典型的20组公路隧道的实测数据为训练样本,建立公路隧道水害倾向性分级的Bayes判别函数。对训练后的模型运用交叉确认估计法进行验证,然后运用该模型对6条待检验的公路隧道样本的水害倾向性进行分级。研究结果表明:构建的Bayes判别分析模型误判率极低,分级效果合理有效,可以运用于公路隧道水害倾向性的分级中,有利于公路隧道水害的预防和治理。
In order to improve the overall safety performance of highway tunnel, ensure personnel safety, reduce property damage, and avoid the flood accident of highway tunnel, the Bayes discriminant theory was applied in flood tendency discrimination and classification of highway tunnel. Seven main indexes influencing the occurrence of tunnel flood, such as permeability coefficient of tunnel area＇, precipitation condition, units-inflow, type of tecton- ic fault zone, surrounding rock classification, situation of tunnel construction and waterproof and drainage measures, were regarded as the basic discriminant factors. The flood tendency of highway tunnel was divided into four grades which were considered as four normal populations in Bayes discriminant analysis. Twenty representative tested data of samples from typical highway tunnel were used as the training samples, and the corresponding Bayes discriminant model was gained. The cross-validated method was introduced to verify the stability of Bayes discriminate model, then the flood tendency of six samples was classified with this model. The results showed that the model has a very low misjudgment rate, and the classification effect is reasonable and effective. It can be applied in flood tendency classification of highway tunnel, and is beneficial for prevention and control on flood of highway tunnel.
出处
《中国安全生产科学技术》
CAS
CSCD
北大核心
2015年第6期120-125,共6页
Journal of Safety Science and Technology
基金
国家"十二五"科技支撑计划项目(2012BAC09B02)
湖南省科技重大专项计划项目(2011FJ1003-3)
关键词
公路隧道
Bayes判别分析
水害
倾向性
分级
highway tunnel
Bayes discriminant analysis
flood
tendency
classification
