[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122409-en":3,"doc-seo-122409-105":30,"detail-sidebar-cat-0-en-105":91},{"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":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122409,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",6,"Technology","Machine Learning Method for As-Is Tunnel Information Model Reconstruction - Paper","Aging road tunnel maintenance requires efficient inspection and planning tools. The paper proposes a methodology that segments and classifies tunnel point clouds from laser surveys, addressing the data overload problem. Point clouds from four Italian tunnels are divided into segments, clustered into homogeneous groups, and manually labeled to train machine learning models. Classified points representing lining, road surfaces, and equipment are converted into a 3D mesh model and exported in OpenBIM format to support seamless data exchange and improve maintenance workflows.","1 Machine Learning Method for As-Is Tunnel Information  \n2 Model Reconstruction.  \n3 Nicola Rimellaa*, Lorenzo Rimellab, Anna Oselloa  \n4 aDISEG, Politecnico di Torino, Corso Duca degli Abruzzi, 24, 10129 Turin, Italy  \n5 b ESOMAS, Universitá degli studi di Torino and Collegio Carlo Alberto, Piazza Vincenzo  \n6 Arbarello, 8, 10122, Turin, Italy  \n7 ∗ Corresponding author: nicola.rimella@polito.it  \n8 Abstract  \n9 The maintenance of aging infrastructure requires advanced tools for efficient inspection and  \n10 planning. This paper presents a methodology for segmenting and classifying point clouds of road 11 tunnels to streamline maintenance operations. Processing large datasets, such as those generated 12 by laser surveys, poses significant challenges without appropriate IT solutions. Data from four Italian 13 tunnels were divided into segments and clustered into homogeneous groups. These clusters were 14 manually classified to create a labeled dataset for training machine learning algorithms. The 15 classified points, representing elements such as lining, road surfaces, and equipment, were then 16 used to generate a 3D mesh model. By sharing the results in the OpenBIM format , the method 17 facilitates seamless data exchange among infrastructure maintenance professionals, improving 18 efficiency in planning and execution.  \n19  \n20 Keywords: Machine Learning-Clustering and Classification, Point Cloud, 3D reconstruction, Maintenance, 21 Tunnelling, Building Information Model  \n22 1. Introduction  \n23 As described in [1], the status of Italian tunnels in the Trans-European Network (TERN) is difficult to  \n24 manage. Approximately half of the total number of sections and lengths developments of TERN  \n25 tunnels are in Italy and half of them have been in operation for more than 30 years. These structures  \n26 need improvements, especially from a structural perspective. The same report [1] shows the data  \n27 provided by the operators on the 31st of December 2020, revealing that only 18% of the TERN  \n28 tunnels comply with the current regulations. The latest technologies, such as laser devices for  \n29 collecting data on-site [2], can aid in describing complex structures, such as tunnels.  \n30 However, laser instruments produce an enormous amount of data that must be meticulously  \n31 screened and cleared of unnecessary or unmanageable information before it can be used in the  \n32 design process. To improve understanding of this big data, machine learning techniques can be  \n33 used to support data screening [3] . A large-scale survey and investigation campaign has been  \n34 undertaken in Italy to monitor the condition of underground infrastructure. The current investigation  \n35 practice follows the guidelines in [4], using a layered approach to evaluate and understand the  \n36 infrastructure. Level 0 involves taking a census of the structures in the territory that require  \n37 renovation, including data on their geographical locations, maintenance histories, and other relevant  \n38 details. Level 1 focuses on initial inspections and the processing of defect records. During this phase, 39 it is also essential to gather information on the volume of the subsurface, identify visible defects  \n40 through surveys, and perform geometric surveys. Level 2 involves analyzing the collected data and  \n41 assigning an attention class to the infrastructure to evaluate its condition and determine if future  \n42 investigations and monitoring are needed. Level 3 provides an in-depth research campaign to  \n43 estimate the instabilities related to the interaction of the lining with the natural formations it crosses.  \n44 At this level, a point cloud of the tunnel is created. Level 4 provides accurate safety evaluations of  \n45 the tunnel, based on the active danger and external environment factor. Lastly, Level 5 evaluates  \n46 the importance of the infrastructure in the road network and the socio-economic context related to a  \n47 hypothetical s","cbCain3DQB5XsFSK","https://ap.wps.com/l/cbCain3DQB5XsFSK","pdf",2021120,1,21,"English","en",105,"# Abstract\n# Keywords\n# 1. Introduction\n## Multi-level investigation approach\n## Laser scanning and data processing\n## OpenBIM workflow and motivation","[{\"question\":\"What is the main goal of the proposed methodology?\",\"answer\":\"To streamline tunnel maintenance by segmenting and classifying tunnel point clouds and reconstructing a 3D model for BIM-based workflows.\"},{\"question\":\"How is labeled training data created for machine learning?\",\"answer\":\"Data from four tunnels are segmented and clustered into homogeneous groups, which are then manually classified to form a labeled dataset for training.\"},{\"question\":\"What output format does the method produce to support collaboration?\",\"answer\":\"The reconstructed results are shared in the OpenBIM format to enable seamless data exchange among infrastructure maintenance professionals.\"}]","Machine Learning Method for As-Is Tunnel Information Model Reconstruction - Paper | PDF",1785810482,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-method-for-as-is-tunnel-information-model-reconstruction-paper","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-method-for-as-is-tunnel-information-model-reconstruction-paper/122409/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of the proposed methodology?","Question",{"text":75,"@type":76},"To streamline tunnel maintenance by segmenting and classifying tunnel point clouds and reconstructing a 3D model for BIM-based workflows.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is labeled training data created for machine learning?",{"text":80,"@type":76},"Data from four tunnels are segmented and clustered into homogeneous groups, which are then manually classified to form a labeled dataset for training.",{"name":82,"@type":73,"acceptedAnswer":83},"What output format does the method produce to support collaboration?",{"text":84,"@type":76},"The reconstructed results are shared in the OpenBIM format to enable seamless data exchange among infrastructure maintenance professionals.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]