[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124322-en":3,"doc-seo-124322-105":29,"detail-sidebar-cat-0-en-105":94},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},124322,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Enhancing Rock Mass Classification in TBM Tunnelling Using Ensemble Machine Learning Algorithms","Ensemble machine learning addresses limitations of empirical rock mass classification in TBM tunnelling under complex Himalayan geology. The study preprocesses a TBM database of 2,859 segmental rings from a double shield TBM tunnel in Nepal Himalaya, then trains bagging, boosting, and random forest models with optimized hyperparameters. Model performance is validated on separate test data using evaluation metrics. Random forest achieves the highest classification accuracy at 94%. Key operational parameters are linked to rock mass quality: PRnet, PRchd, and CRS show negative influence, while thrust and torque show positive effects, providing actionable insight for TBM control.","ARMA 25–0061  \nEnhancing Rock Mass Classification in TBM Tunnelling Using Ensemble Machine Learning Algorithms  \nTek Bahadur Katuwal and Krishna Kanta Panthi  \nNorwegian University of Science and Technology (NTNU), Trondheim, Norway  \nCopyright 2025 ARMA, American Rock Mechanics Association  \nThis paper was prepared for presentation at the 59th US Rock Mechanics/Geomechanics Symposium held in Santa Fe, New Mexico , USA, 8-11 June 2025. This paper was selected for presentation at the symposium by an ARMA Technical Program Committee based on a technical and critical review of the paper by a minimum of two technical reviewers. The material, as presented, does not necessarily reflect any position of ARMA, its officers, or members. Electronic reproduction, distribution, or storage of any part of this paper for commercial purposes without the written consent of ARMA is prohibited. Permission to reproduce in print is restricted to an abstract of not more than 200 words; illustrations may not be copied. The abstract must contain conspicuous acknowledgement of where and by whom the paper was presented.  \nABSTRACT: It is common practice to use empirical rock mass classification systems for rock mass characterization in TBM tunnelling. However, complex geological conditions and limited access to the tunnel face significantly impact rock mass classification. The aim of this study is to address existing limitations by applying ensemble machine learning algorithms such as bagging, boosting, and random forest to characterize rock mass conditions using machine operational and geological parameters of double shield TBM tunnel excavated in Nepal Himalaya. To do so, the TBM database of 2,859 segmental rings were preprocessed and transferred into a usable format. The database then split into training and testing sets and the selected algorithms were trained with a training set with optimal hypermeters. The performance of trained models was validated with test database. Based on a comparison of evaluation metrics, the random forest model demonstrated superior performance for rock mass classification, achieving the highest accuracy of 94% . Notably, the net penetration rate (PRnet), cutter head penetration rate (PRchd), and cutter head speed (CRS) exhibited a negative impact on rock mass quality, while thrust and torque showed a positive influence. These findings provide critical insights into the relationship between TBM operational parameters and rock mass quality.  \n1. INTRODUCTION  \nThe rock mass conditions in the Himalayan region are highly uncertain due to the presence of higher degrees of faulting, folding, jointing, and weathering. Additionally, shear and weakness zones often appeared in this region (Panthi, 2006) . Consequently, tunnelling in the Himalayan region is very complex, and challenging, necessitating careful rock mass classification and appropriate tunnelling techniques for such geological conditions (Panthi, 2019; Katuwal et al., 2023) .  \nTunnel Boring Machine (TBM) excavation techniques have been extensively used for long-length tunnels due to its high excavation rate, good construction efficiency, and environment friendly as compared to the drill and blast excavation techniques (Macias and Bruland, 2014; Panthi, 2019; Zhang et al., 2019) . Nonetheless, varying rock mass conditions in the Himalayan geology greatly influence the tunnelling performance. Thus, rock mass classification requires special attention for the timely completion of tunnelling projects in the Himalayan region (Panthi, 2019; Katuwal and Panthi, 2024) . Mostly, the RMR-system by Bieniawski (1989) and Q-system suggested by Barton et al. (1974) are used in the Nepal Himalayas for rock mass quality evaluation and rock support design work. However, in TBM tunnelling, the  \nface mapping to find out rock mass quality class is a challenging task.  \nIn TBM tunnelling, the space between the tunnel face and the TBM cutter head is both inaccessible and limited, leaving","cbCaikvmJn0GnzQi","https://ap.wps.com/l/cbCaikvmJn0GnzQi","pdf",1005266,1,"English","en",105,"# Abstract\n## Introduction\n## Problem of rock mass classification in TBM tunnelling\n## Role of TBM operational parameters and machine learning approach","[{\"question\":\"What problem does the study target in TBM tunnelling rock mass classification?\",\"answer\":\"Empirical classification systems struggle under complex geology and limited face-mapping access, increasing uncertainty. The study targets these limitations by learning from machine operational and geological parameters.\"},{\"question\":\"Which ensemble algorithms are applied and how is the dataset handled?\",\"answer\":\"Bagging, boosting, and random forest are used. The TBM dataset of 2,859 segmental rings is preprocessed, split into training and testing sets, and models are trained with optimal hyperparameters.\"},{\"question\":\"Which model performs best and what accuracy is achieved?\",\"answer\":\"The random forest model shows superior performance, reaching the highest accuracy of 94% for rock mass classification.\"},{\"question\":\"How do TBM operational parameters relate to rock mass quality in the results?\",\"answer\":\"Net penetration rate (PRnet), cutter head penetration rate (PRchd), and cutter head speed (CRS) negatively affect rock mass quality, while thrust and torque positively influence it.\"}]","Enhancing Rock Mass Classification in TBM Tunnelling Using Ensemble Machine Learning Algorithms | PDF",1785821599,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":89,"head_meta":91,"extra_data":93,"updated_unix":27},"enhancing-rock-mass-classification-in-tbm-tunnelling-using-ensemble-machine-learning-algorithms","",{"@graph":35,"@context":88},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/enhancing-rock-mass-classification-in-tbm-tunnelling-using-ensemble-machine-learning-algorithms/124322/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80,84],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the study target in TBM tunnelling rock mass classification?","Question",{"text":74,"@type":75},"Empirical classification systems struggle under complex geology and limited face-mapping access, increasing uncertainty. The study targets these limitations by learning from machine operational and geological parameters.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which ensemble algorithms are applied and how is the dataset handled?",{"text":79,"@type":75},"Bagging, boosting, and random forest are used. The TBM dataset of 2,859 segmental rings is preprocessed, split into training and testing sets, and models are trained with optimal hyperparameters.",{"name":81,"@type":72,"acceptedAnswer":82},"Which model performs best and what accuracy is achieved?",{"text":83,"@type":75},"The random forest model shows superior performance, reaching the highest accuracy of 94% for rock mass classification.",{"name":85,"@type":72,"acceptedAnswer":86},"How do TBM operational parameters relate to rock mass quality in the results?",{"text":87,"@type":75},"Net penetration rate (PRnet), cutter head penetration rate (PRchd), and cutter head speed (CRS) negatively affect rock mass quality, while thrust and torque positively influence it.","https://schema.org",{"og:url":51,"og:type":90,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":92,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":95},[96,100,104,108,113,118,123,126,130,133,137],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},"Exam",70,"exam",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},5,"Comic",60,"comic",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},6,"Technology",50,"technology",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":121,"slug":122},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":124,"slug":125},30,"research-report",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":28,"slug":129},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":28,"slug":132},"World Cup","world-cup",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":134,"slug":136},10,"Lifestyle","lifestyle",{"id":138,"doc_module":4,"doc_module_name":45,"category_name":139,"show_sort_weight":109,"slug":140},19,"General","general"]