深埋特长的云雾山隧道涌水影响因素及涌水量预测  

Prediction of Gushing Water and Influencing Factors in Deep Buried Super Long Tunnel for Yunwushan

作　　者：苏昭[1] SU Zhao(Shaanxi Railway Institute,Weinan 714000,China)

机构地区：[1]陕西铁路工程职业技术学院

出　　处：《水电能源科学》2019年第12期58-61,共4页Water Resources and Power

基　　金：陕西铁路工程职业技术学院2019年科研基金项目(KY2019-10);陕西铁路工程职业技术学院建筑施工技术科技创新团队基金(KJTD201804)

摘　　要：为合理评价不同隧道涌水影响因素的影响程度,基于现场监测结果,采用数量化理论Ⅲ筛选各涌水影响因素的影响程度及其耦合强度,并利用极限学习机构建了隧道涌水量预测模型,进而实现隧道涌水影响因素分析及涌水量预测的综合评价。实例研究表明,隧道涌水影响因素之间的耦合度均偏高,隧道涌水受多种影响因素的综合作用,并不是单一影响因素作用的结果;另外,基于数量化理论Ⅲ分析结果构建的极限学习机模型可有效预测隧道涌水量,且通过试算法和混沌理论能进一步提高预测精度,验证了该模型在隧道涌水量预测中的适用性和可靠性。In order to reasonably evaluate the influence degree of different influencing factors of tunnel gushing water,based on the field monitoring results,this paper adopts quantitative theory Ⅲ to screen the influence degree and coupling strength of influencing factors of tunnel gushing water.The extreme learning machine is used to establish prediction model of tunnel gushing water and realize the comprehensive evaluation of influencing factors of tunnel gushing water and prediction of gushing water.Case study shows that the coupling degree between influencing factors of tunnel gushing water is high,and it is concluded that tunnel gushing water is affected by a variety of factors,not by a single factor.In addition,the extreme learning machine model based on the results of quantitative theoryⅢ analysis can effectively predict tunnel gushing water,and the prediction accuracy can be further improved by trial algorithm and chaos theory.The applicability and reliability of the model in the prediction of tunnel gushing water are verified.

关 键 词：特长隧道 数量化理论Ⅲ 涌水影响因素 极限学习机 涌水量预测 

分 类 号：U456.3[建筑科学—桥梁与隧道工程]