摘要
盾构隧道施工不可避免会引起地表沉降,影响周边建构筑物安全。随着国内超大直径盾构隧道建设逐渐增多,其施工引起地表沉降的规律与预测方法研究亟待进一步拓展。针对超大直径盾构隧道开挖引起的地表沉降问题,基于某超大直径越江隧道工程搜集的数据,采用机器学习的方法对地表沉降进行预测,建立了基于梯度提升决策树模型(GBDT)的沉降预测模型。通过交叉验证算法(CV)和网格搜索算法(GS)对该模型进行优化,得到改进后的GBDT-GSCV沉降预测模型,并进行了模型验证。结果表明,GBDT-GSCV模型用于地表沉降预测适应性较好。将GBDT-GSCV模型的结果与现有的其它模型进行比较,结果表明该模型具有更好的准确性与鲁棒性。
Shield tunneling will inevitably cause ground settlement and affect the safety of surrounding structures.Along with the gradual increase construction of super-large diameter shield tunnel in China,the research on the laws and prediction methods of surface settlement caused by these constructions needs further improvement.Aiming at the problem of surface settlement caused by the excavation of a super-large diameter shield tunnel,this paper uses machine learning methods to predict the surface settlement based on the data collected by a super-large diameter cross-river tunnel project,and establishes a prediction model based on the gradient boosting decision tree model(GBDT).Cross validation algorithm(CV)and grid search algorithm(GS)are used to optimize the model,and the improved GBDT-GSCV settlement prediction model is obtained and validated.The results show that the GBDT-GSCV model is used to predict surface settlement and adapts well.Comparing the results of GBDT-GSCV model with other existing models,the results show that this model has better accuracy and robustness.
作者
陈阳阳
陈健
骆汉宾
Chen Yangyang;Chen Jian;Luo Hanbin(School of Civil&Hydraulic Engineering,Huazhong University of Science&Technology,Wuhan 430074,P.R.China;National Center of Technology Innovation for Digital Construction of China,Wuhan 430074,P.R.China)
出处
《地下空间与工程学报》
CSCD
北大核心
2022年第S01期379-384,395,共7页
Chinese Journal of Underground Space and Engineering
基金
国家自然科学基金重点项目(52192664,71732001)
湖北省重大科技专项(2020ACA006)
关键词
梯度提升决策树
网格搜索
k折交叉验证
地表沉降
鲁棒性
gradient boosting decision tree
grid search
k-fold cross validation
surface settlement
robustness