[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-651110-105":59,"doc-detail-651110-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","pan-recovering-building-information-model-from-2d","Pan Recovering Building Information Model from 2D","","Ageing buildings face growing pressure due to inadequate management and maintenance of Mechanical, Electrical, and Plumbing (MEP) systems, while Building Information Modelling (BIM) supports efficient MEP operation and maintenance through digital system representations. Many ageing buildings lack BIM, and manual reconstruction is costly. This work proposes an automatic approach to recover MEP BIM from 2D drawings using semantic extraction with Cascade Mask R-CNN, geometric extraction for contours and skeletons, and IFC-based reconstruction with pythonOCC and IfcOpenShell. Experiments on two MEP systems show strong accuracy and efficiency.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/pan-recovering-building-information-model-from-2d/651110/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/pan-recovering-building-information-model-from-2d/651110.png","ImageObject",300,407,{"name":92,"@type":93},"Dewi_Sukmawati","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-24",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is recovering BIM for ageing buildings important for MEP operation and maintenance?","Question",{"text":112,"@type":113},"Ageing buildings often lack BIM, which makes efficient retrieval and use of MEP information difficult. BIM supports O&M by providing structured geometry and semantics for MEP systems.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What are the three modules in the proposed automatic method?",{"text":117,"@type":113},"The method uses semantic extraction (image cropping with Cascade Mask R-CNN), geometric extraction (semantic-assisted contour and skeleton extraction), and IFC-based BIM reconstruction using pythonOCC and IfcOpenShell.",{"name":119,"@type":110,"acceptedAnswer":120},"How was the method evaluated, and what performance results were reported?",{"text":121,"@type":113},"The approach was tested on two MEP systems containing 335 and 282 multiscale, irregular elements. It recovered BIMs in 2.85 seconds and 0.79 seconds, with semantic extraction accuracy above 0.9 and geometric error below 5%.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},651110,1793030780,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},962094243415,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","1 Article  \n2 Recovering Building Information Model from 2D  \n3 Drawings for Mechanical, Electrical and Plumbing  \n4 Systems of Ageing Buildings  \n5 Pan, Zaolina Yu, Yantaoa * Xiao, Fub, c Zhang, Jingb  \n6 a Department of Civil and Environmental Engineering, The Hong Kong University  \n7 of Science and Technology, Hong Kong, China  \n8 b Department of Building Environment and Energy Engineering, The Hong Kong  \n9 Polytechnic University, Hong Kong, China  \n10 c Research Institute for Smart Energy, The Hong Kong Polytechnic University, 11 Hong Kong, China  \n12 * Correspondence: [ceyantao@ust.hk](ceyantao@ust.hk)[ ](ceyantao@ust.hk)13  \n14 Abstract: Ageing buildings have become a significant concern for many cities, 15 exacerbated by inadequate management and maintenance of Mechanical, Electrical, 16 and Plumbing (MEP) systems, and Building Information Modelling (BIM) enables  \n17 efficient MEP Operation and Maintenance (O&M) through the digital representation  \n18 of system information; however, many ageing buildings were constructed without  \n19 BIM, and manual reconstruction is costly and inefficient due to the sheer number of  \n20 such structures. Although some studies have proposed methods for automatically  \n21 recovering BIM from 2D drawings, few are suitable for MEP systems due to the  \n22 multiscale and irregular shapes of MEP components. To fill this gap, an automatic  \n23 approach is proposed for recovering MEP BIM from 2D drawings with three modules:  \n24 1) semantic extraction by combining image cropping with Cascade Mask R-CNN to 25 detect and segment multiscale, irregular MEP components; 2) geometric extraction by 26 semantic-assisted image processing to extract contours and skeletons of irregular parts;  \n27 and 3) Industry Foundation Class (IFC)-based BIM reconstruction via the open-source  \n28 pythonOCC and IfcOpenShell. The performance was tested on two MEP systems with  \n29 335 and 282 multiscale and irregular elements, and the results show that the method  \n30 recovered BIMs for the two MEP systems in 2.85 seconds and 0.79 seconds, with  \n31 semantic extraction accuracy exceeding 0.9 and geometric error below 5% . This paper  \n32 contributes to the existing body of knowledge by providing a semantic and geometric- 33 based approach for recovering multiscale and irregular components from 2D drawings.  \n34 Future studies could further improve the approach by integrating elevation drawings, 35 reconstructing abstract symbols, and aligning text-geometry.  \n36  \n37 Keywords: Building Information Model (BIM); Industry Foundation Classes (IFC);  \n38 Mechanical, Electrical, and Plumbing (MEP) Systems; BIM Reconstruction;  \n39 Operation and Maintenance (O&M)  \n40 1. Introduction  \n41 Deteriorating energy performance of ageing buildings challenges energy  \n42 conservation and emission reduction [1] . Evidence suggests that ageing buildings over  \n43 50 years old in Europe account for 35% of existing buildings and are responsible for 44 40% of energy consumption and 36% of CO2 emissions in the EU [2] . Effective  \n45 Operation and Maintenance (O&M) of Mechanical, Electrical, and Plumbing (MEP)  \n46 systems may reduce the energy consumption and greenhouse gas emissions of an  \n47 ageing building. It is estimated that up to 16% of MEP systems' energy consumption  \n48 during building operations can be saved through proper management [3] .  \n49 Traditional MEP system O&M methods typically retrieve information through  \n50 manual review of as-built drawings and documents [4], which are complex and error- 51 prone [5] . Building Information Model (BIM 1) contains rich information on geometry  \n52 and semantics and can improve and simplify the information retrieval process by  \n53 providing practical data support for the O&M of the MEP systems [6] . The data and  \n54 knowledge extracted and discovered from BIM, such as the MEP-related entities and  \n55 relationships [7], the MEP logic chain [8], and the grouping and labelling of ","cbCaijgTM0gjtqiT","https://ap.wps.com/l/cbCaijgTM0gjtqiT","pdf",2822766,32,"English","# Abstract\n# 1. Introduction","[{\"question\":\"Why is recovering BIM for ageing buildings important for MEP operation and maintenance?\",\"answer\":\"Ageing buildings often lack BIM, which makes efficient retrieval and use of MEP information difficult. BIM supports O\\u0026M by providing structured geometry and semantics for MEP systems.\"},{\"question\":\"What are the three modules in the proposed automatic method?\",\"answer\":\"The method uses semantic extraction (image cropping with Cascade Mask R-CNN), geometric extraction (semantic-assisted contour and skeleton extraction), and IFC-based BIM reconstruction using pythonOCC and IfcOpenShell.\"},{\"question\":\"How was the method evaluated, and what performance results were reported?\",\"answer\":\"The approach was tested on two MEP systems containing 335 and 282 multiscale, irregular elements. It recovered BIMs in 2.85 seconds and 0.79 seconds, with semantic extraction accuracy above 0.9 and geometric error below 5%.\"}]","Pan Recovering Building Information Model from 2D | PDF",1792862888,81]