Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization

作     者：Jian Zhou Yingui Qiu Shuangli Zhu Danial Jahed Armaghani Manoj Khandelwal Edy Tonnizam Mohamad 

作者机构：School of Resources and Safety EngineeringCentral South UniversityChangsha 410083China Department of Civil EngineeringFaculty of EngineeringUniversity of Malaya50603 Kuala LumpurMalaysia School of EngineeringInformation Technology and Physical SciencesFederation University AustraliaBallaratAustralia Centre of Tropical Geoengineering(GEOTROPIK)School of Civil EngineeringFaculty of EngineeringUniversiti Teknologi Malaysia81310 Johor BahruMalaysia 

出 版 物：《Underground Space》 (地下空间（英文）)

年 卷 期：2021年第6卷第5期

页      面：506-515页

核心收录：

学科分类：081406[工学-桥梁与隧道工程] 08[工学] 0814[工学-土木工程] 082301[工学-道路与铁道工程] 0823[工学-交通运输工程] 

基　　金：funded by the National Science Foundation of China(41807259) the Innovation-Driven Project of Central South University(2020CX040),China the Shenghua Lieying Program of Central South University,China(Principle Investigator:Dr.Jian Zhou) 

主　　题：TBM performance Advance rate XGBoost Bayesian optimization Predictive modeling 

摘      要：The advance rate(AR)of a tunnel boring machine(TBM)under hard rock conditions is a key parameter in the successful implementation of tunneling *** this study,we improved the accuracy of prediction models by employing a hybrid model of extreme gradient boosting(XGBoost)with Bayesian optimization(BO)to model the TBM *** develop the proposed models,1286 sets of data were collected from the Peng Selangor Raw Water Transfer tunnel project in *** database consists of rock mass and intact rock features,including rock mass rating,rock quality designation,weathered zone,uniaxial compressive strength,and Brazilian tensile *** specifications,including revolution per minute and thrust force,were considered to predict the TBM *** accuracies of the predictive models were examined using the root mean squares error(RMSE)and the coefficient of determination(R^(2))between the observed and predicted yield by employing a five-fold cross-validation *** showed that the BO algorithm can capture better hyper-parameters for the XGBoost prediction model than can the default XGBoost *** robustness and generalization of the BO-XGBoost model yielded prominent results with RMSE and R^(2) values of 0.0967 and 0.9806(for the testing phase),*** results demonstrated the merits of the proposed BO-XGBoost *** addition,variable importance through mutual information tests was applied to interpret the XGBoost model and demonstrated that machine parameters have the greatest impact as compared to rock mass and material properties.