[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-650634-105":59,"doc-detail-650634-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","automatic-digitization-of-engineering-diagrams-using-deep-learning-and-graph-search","Automatic Digitization of Engineering Diagrams using Deep Learning and Graph Search","","A Piping and Instrumentation Diagram (P&ID) uses standardized symbols, text, and lines to represent equipment and the flow of an industrial process, yet it is often stored as image files with little metadata. This creates search and integration barriers between diagram content and operational or enterprise systems. The proposed pipeline automatically digitizes P&IDs by detecting symbols, linking symbols with nearby text, and tracing connections via graph search, enabling diagram search, equipment-to-sensor mapping, and asset hierarchy creation.",{"@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/automatic-digitization-of-engineering-diagrams-using-deep-learning-and-graph-search/650634/",{"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/automatic-digitization-of-engineering-diagrams-using-deep-learning-and-graph-search/650634.png","ImageObject",300,407,{"name":92,"@type":93},"Ophelia","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-24",true,{"@type":102,"interactionType":103,"userInteractionCount":19},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the paper address in P&ID digitization?","Question",{"text":112,"@type":113},"P&IDs are frequently trapped in image files with limited metadata, making their contents hard to search and difficult to connect to operational or enterprise systems.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed pipeline extract information from P&IDs?",{"text":117,"@type":113},"It detects symbols with a trained convolutional neural network, matches symbols with associated text, and uses a graph search approach to traverse diagram lines and find interconnected symbols.",{"name":119,"@type":110,"acceptedAnswer":120},"What applications does digitizing P&IDs enable?",{"text":121,"@type":113},"The structured asset hierarchy supports diagram search, equipment-to-sensor mapping, asset hierarchy creation, and—when combined with operational data—facility-wide digital twin use cases such as predictive maintenance.","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},650634,1793076807,{"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":19,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":34,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144},7971461741311,"https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826","Automatic Digitization of Engineering Diagrams using Deep Learning and Graph Search  \nShouvik Mani, Michael A. Haddad, Dan Constantini, Willy Douhard, Qiwei Li, Louis Poirier  \n[C3.ai](C3.ai)  \n{ [firstname.lastname](firstname.lastname}@c3.ai)[}](firstname.lastname}@c3.ai)[@c3.ai](firstname.lastname}@c3.ai)  \nAbstract  \nA Piping and Instrumentation Diagram (P&ID) is a typeof engineering diagram that uses symbols, text, and lines to represent the components and 􀀃ow of an industrial process. Although used universally across industries such as manufacturing and oil & gas, P&IDs are usually trapped in image 􀀂les with limited metadata, making their contentsunsearchable and siloed from operational or enterprise systems. In order to extract the information contained in these diagrams, we propose a pipeline for automatically digitizing P&IDs. Our pipeline combines a series of computer vision techniques to detect symbols in a diagram, match symbols with associated text, and detect connections between symbols through lines. For the symbol detection task, we train a Convolutional Neural Network to classify certain common symbols with over 90% precision and recall. To detect connections between symbols, we use a graph search approach to traverse a diagram through its lines and discover interconnected symbols. By transforming unstructured diagrams into structured information, our pipeline enables applications such as diagram search, equipmentto-sensor mapping, and asset hierarchy creation. When integrated with operational and enterprise data, the extracted asset hierarchy serves as the foundation for a facility-wide digital twin, enabling advanced applications such as machine learning-based predictive maintenance.  \n1. Introduction  \nEngineering designs, such as Piping and Instrumentation Diagrams (P&IDs), are used throughout the entire lifecycle of a facility. Created during the engineering and design phase, they are used to communicate requirements throughout the construction and operational phases of an industrial facility. In many jurisdictions, primarily for safety considerations, there are legal requirements to keep these designs up to date with any changes. Additionally, process engineers rely primarily on P&IDs to understand an industrial process  \nand as a tool to plan and implement process changes. These factors make P&IDs a valuable, up to date ground-truth data source for the con􀀂guration of an industrial facility. However, P&IDs are often archived as hundreds of CAD 􀀂les per facility with limited or no metadata describing the components, connections between components, or connections between P&IDs.  \nAs IoT sensors have proliferated throughout industrial facilities they have become an important element of P&IDs. These sensors, commonly referred to as tags, provide critical, real-time operational data (e.g., temperature, pressure,􀀃ow, etc.) and are often connected to locally mounted instruments (LMIs) or installed directly onto equipment. This real-time operational data has become increasingly important for plant management, asset performance management, and process optimization. As machine learning techniques evolve to extract even more value from this data, contextualizing these tags within diagrams and referencing them to external sensor management systems is an increasingly critical pre-processing step. For an end user of an AI application to properly interpret machine learning predictions they must have a clearly de􀀂ned asset hierarchy with sensor locations. For example, when implementing anomaly detection, a well-de􀀂ned asset hierarchy will enable a user to localize an anomalous sensor within a facility and identify a particular component of the machinery.  \nPerforming the contextualization step manually on P&IDs is time consuming and error prone. Our digitization pipeline aims to automate this step by combining stateof-the-art computer vision, graph search, and optical character recognition techniques to map the intercon","cbCaim6LHR06femI","https://ap.wps.com/l/cbCaim6LHR06femI","pdf",1479313,"English","# 1. Introduction\n# 2. Related work","[{\"question\":\"What problem does the paper address in P\\u0026ID digitization?\",\"answer\":\"P\\u0026IDs are frequently trapped in image files with limited metadata, making their contents hard to search and difficult to connect to operational or enterprise systems.\"},{\"question\":\"How does the proposed pipeline extract information from P\\u0026IDs?\",\"answer\":\"It detects symbols with a trained convolutional neural network, matches symbols with associated text, and uses a graph search approach to traverse diagram lines and find interconnected symbols.\"},{\"question\":\"What applications does digitizing P\\u0026IDs enable?\",\"answer\":\"The structured asset hierarchy supports diagram search, equipment-to-sensor mapping, asset hierarchy creation, and—when combined with operational data—facility-wide digital twin use cases such as predictive maintenance.\"}]","Automatic Digitization of Engineering Diagrams using Deep Learning and Graph Search | PDF",1792835187,18]