基于混沌-RF-SVM变形预测模型的隧道运营安全状况分析  

Safety analysis of tunnel operation based on Chaos-RF-SVM deformation prediction model

作　　者：黄阿岗[1] 何军[2] 郝付军[1] HUANG Agang;HE Jun;HAO Fujun(Shaanxi Railway Institute,Weinan 714000,China;Henan Polytechnic University,Jiaozuo 454000, China)

机构地区：[1]陕西铁路工程职业技术学院,陕西渭南714000 [2]河南理工大学,河南焦作454000

出　　处：《测绘工程》2022年第4期52-56,共5页Engineering of Surveying and Mapping

基　　金：陕西省渭南市2019年科研计划项目(2019ZDYF-JCYJ-129);陕西铁路工程职业技术学院2019年科研基金项目计划(KY2019-52)。

摘　　要：为合理评价隧道运营状况,基于运营隧道现场变形监测成果,先利用混沌理论、随机森林算法和支持向量机构建变形预测模型,再利用M-K检验等进行预测结果的可靠性验证分析,两者结合评价隧道运营状况。实例分析表明,在变形预测过程中,预测结果的平均相对误差均小于2%,具有较高的预测精度;同时,经可靠性验证,趋势判断结果与预测结果较为一致,均得出隧道变形仍会进一步增加,但增加速率变小,趋于稳定方向发展,即会维持现有运营状况。In order to reasonably evaluate the tunnel operation status,based on the deformation monitoring results of the operating tunnel,the deformation prediction model is established by using chaos theory,random forest algorithm and support vector machine,and then the reliability of the prediction results is verified and analyzed by using M-K test.The example analysis shows that:in the process of deformation prediction,the average relative error of prediction results is less than 2%,which has high prediction accuracy;at the same time,through the reliability verification,the trend judgment results are consistent with the prediction results.It is concluded that the tunnel deformation will continue to increase,but the increase rate is small and tends to be stable,that is,the existing operation status will be maintained.

关 键 词：运营隧道 混沌理论 支持向量机 变形预测 M-K检验 

分 类 号：U459.2[建筑科学—桥梁与隧道工程]