Soft ground tunnel lithology classification using clustering-guided light gradient boosting machine

作     者：Kursat Kilic Hajime Ikeda Tsuyoshi Adachi Youhei Kawamura Kursat Kilic;Hajime Ikeda;Tsuyoshi Adachi;Youhei Kawamura

作者机构：Department of GeosciencesGeotechnology and Materials Engineering for ResourcesGraduate School of International Resource SciencesAkita UniversityAkita010-8502Japan Division of Sustainable Resources EngineeringFaculty of EngineeringHokkaido UniversityKita 13Nishi 8Kita-kuSapporo060-8628Japan 

出 版 物：《Journal of Rock Mechanics and Geotechnical Engineering》 (岩石力学与岩土工程学报（英文版）)

年 卷 期：2023年第15卷第11期

页      面：2857-2867页

核心收录：

学科分类：081803[工学-地质工程] 081401[工学-岩土工程] 08[工学] 0818[工学-地质资源与地质工程] 0814[工学-土木工程] 

基　　金：supported by Japan Society for the Promotion of Science KAKENHI(Grant No.JP22H01580) 

主　　题：Earth pressure balance(EPB) Tunnel boring machine(TBM) Soft ground tunnelling Tunnel lithology Operational parameters Synthetic minority oversampling technique (SMOTE) K-means clustering 

摘      要：During tunnel boring machine(TBM)excavation,lithology identification is an important issue to understand tunnelling performance and avoid time-consuming ***,site investigation generally lacks ground samples and the information is subjective,heterogeneous,and imbalanced due to mixed ground *** this study,an unsupervised(K-means)and synthetic minority oversampling technique(SMOTE)-guided light-gradient boosting machine(LightGBM)classifier is proposed to identify the soft ground tunnel classification and determine the imbalanced issue of tunnelling *** the tunnel excavation,an earth pressure balance(EPB)TBM recorded 18 different operational parameters along with the three main tunnel *** proposed model is applied using Python low-code PyCaret ***,four decision tree-based classifiers were obtained in a short time period with automatic hyperparameter tuning to determine the best model for clustering-guided SMOTE *** addition,the Shapley additive explanation(SHAP)was implemented to avoid the model black box *** proposed model was evaluated using different metrics such as accuracy,F1 score,precision,recall,and receiver operating characteristics(ROC)curve to obtain a reasonable outcome for the minority *** shows that the proposed model can provide significant tunnel lithology identification based on the operational parameters of *** proposed method can be applied to heterogeneous tunnel formations with several TBM operational parameters to describe the tunnel lithologies for efficient tunnelling.