基于有效度评价的隧道最大涌水量预测模型研究  

Establishment of combined prediction model for tunnel maximum water-gushing amount based on effectiveness evaluation

作　　者：殷保国 左昌群[2] 李庆年 肖艳艳 YIN Baoguo;ZUO Changqun;LI Qingnian;XIAO Yanyan(Institute of Geological Survey,China University of Geosciences(Wuhan),Wuhan 430074,China;Faculty of Engineering,China University of Geosciences(Wuhan),Wuhan 430074,China)

机构地区：[1]中国地质大学(武汉)地质调查研究院,湖北武汉430074 [2]中国地质大学(武汉)工程学院,湖北武汉430074

出　　处：《人民长江》2022年第8期106-111,共6页Yangtze River

基　　金：国家自然科学基金项目(41920104007)。

摘　　要：隧道涌水对地下工程施工安全和运营稳定影响重大,选择正确的涌水计算模型进行涌水规模预测是展开结构设计和灾害防治的关键。针对目前隧道涌水量预测方法单一、考虑因素不全面导致预测结果失真的这一问题,引入有效度指标,对涌水量计算模型进行了有效度排序,选取最优模型进行组合预测,以达到提高预测精度的目的。以广州地铁21号线施工隧道为研究对象,选用Goodman模型等8种常用的预测模型对隧道最大涌水量分别进行了单项和组合模型预测。通过与地下水实测结果的对比分析得到:引入有效度指标能够定量化评价涌水量预测模型的可靠性,通过组合模型的方式能够提高涌水量预测结果的精度。Tunnel water-gushing is a key and difficult problem in underground engineering construction,which has a significant impact on engineering construction safety and operation stability.Choosing the correct water-gushing calculation model to predict the water-gushing amount is the key to structural design and disaster prevention.In view of the problem that the current estimation of water-gushing amount method is single and the prediction results are distorted due to the incomplete consideration on various factors,the effective degree index is introduced to sort the effective degree of the estimation models of water-gushing amount,and the optimal model is selected and combined to improve the prediction accuracy.Taking the tunnel constructed by mining method of Guangzhou Metro Line 21 as the research object,eight commonly used prediction models such as Goodman model are selected to predict the maximum water-gushing amount of the tunnel by single and combined models.Through the comparison and analysis with the measured results of groundwater,it is concluded that the introduction of effective degree index can quantitatively evaluate the reliability of models of water-gushing amount,and the prediction accuracy of water-gushing amount can be improved by combining different models.

关 键 词：涌水量预测 隧道最大涌水量 有效度指标 组合预测模型 冗余模型 广州地铁 

分 类 号：U61[交通运输工程—船舶及航道工程]