[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122663-en":3,"doc-seo-122663-105":29,"detail-sidebar-cat-0-en-105":90},{"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},122663,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Pathway toward Prior Knowledge-Integrated Machine Learning in Engineering","Amid accelerating digitalization and growing data volumes, the work addresses a persistent gap in engineering: limited progress in domains that require explicit laws and prior knowledge, such as building engineering. It argues that integrating first-principles (logic/physics/rule-based) reasoning with data-driven learning is rarely developed as a process for transferring and using domain knowledge. The study proposes a two-fold framework examining uncertainty sources in knowledge representation and applying knowledge decomposition via a three-tier knowledge-integrated machine learning paradigm.","Pathway toward prior knowledge-integrated machine learning in engineering  \nXia Chen and Philipp Geyer  \nLeibniz University Hannover, Institute for Design and Construction, Sustainable Building Systems  \nGroup, Hannover, 30419, Germany  \nAbstract  \nDespite the digitalization trend and data volume surge, first-principles models (also known as logic-driven, physics-based, rule-based, or knowledge-based models) and data-driven approaches have existed in parallel, mirroring the ongoing AI debate on symbolism versus connectionism. Research for process development to integrate both sides to transfer and utilize domain knowledge in the data-driven process is rare. This study emphasizes efforts and prevailing trends to integrate multidisciplinary domain professions into machine acknowledgeable, data-driven processes in a two-fold organization: examining information uncertainty sources in knowledge representation and exploring knowledge decomposition with a three-tier knowledge-integrated machine learning paradigm. This approach balances holistand reductionist perspectives in the engineering domain.  \nHighlights  \n• A systematic review of philosophical mindset in current methodologies: reductionism and holism.  \n• No Free Lunch (NFL) in knowledge representation and problem formalization leads to performance gapsand uncertainties in the building engineering domain.  \n• Knowledge decomposition paves the path toward knowledge-integrated machine learning - a threelevel ladder of integration paradigms.  \n• Reconciling holism and reductionism methods contributes to effective engineering solutions.  \nIntroduction  \nModeling, forecasting, and optimizing engineering scenarios as inverse problems with hidden physics are often effort-wisely expensive and require different firstprinciples or symbolism formulations (Karniadakis et al. 2021) . Meanwhile, rapid advancements in artificial intelligence (AI) have attracted attention across a variety of fields. However, significant progress has been observed in areas where the data is fundamental and advantageous, but progress is slower in domains reliant on explicit laws and prior knowledge, such as in building engineering.  \nFirst-principles models, rooted in a reductionism philosophy (Andersen 2001), logically decompose, abstract, and deduce the underlying principles of a given phenomenon to formulate symbol-based rules (Minsky 1991) as a concise and abstract representation. These rules  \nhold strong validity when it comes to extrapolation problems and scenario generalizations, hence naturally fit for aligning engineering principles and conducting validation when exploring the design process, e.g., building design with structural engineering. However, these pre-defined, symbolic-based rigid clarity limits their ability to handle cases that lack information definition context or do not fit the rigid rule constraints. Such inflexible architectures and organizational limitations become increasingly pronounced in the face of objectivesin multidisciplinary challenges that demand more comprehensive and nuanced definitions of system modeling, such as sustainability (Westermann and Evins 2019). The advantages of pre-defined, context-based rules transform into significant drawbacks of performing efficient searching, manipulating, and validating elements in complex situations, highlighting the need for a more flexible and adaptable modeling approach.  \nMachine learning (ML) methods, currently dominated by a connectionist approach (Elman 2005), have succeeded in various data-rich fields (L’heureux et al. 2017) . These models primarily rely on heuristic connections to learn the mapping between data inputs and outputs, making them broadly applicable through the universal approximation, end-to-end behavior. However, their generalized approach also leads to heavy data reliance and datahungry issues, as the model organization and approaching mechanisms are not specifically tailored based on the domain data characteri","cbCaifJUNBpE6r25","https://ap.wps.com/l/cbCaifJUNBpE6r25","pdf",1301321,1,"English","en",105,"# Abstract\n## Highlights\n## Introduction\n## Knowledge-Integrated Machine Learning Proposal\n### Representation bias across approaches\n### Uncertainty and performance gaps in engineering","[{\"question\":\"为什么在建筑工程等依赖先验知识的领域中，机器学习进展相对较慢？\",\"answer\":\"文中指出，数据驱动方法在工程领域往往需要明确的领域规律与先验知识支持，而缺乏充分的数据或难以建模物理反问题时会导致性能差距与不确定性。\"},{\"question\":\"研究提出了哪些方式来整合第一性原理模型与数据驱动方法？\",\"answer\":\"研究强调在知识表征中分析信息不确定性的来源，并通过三层次的知识分解范式构建知识整合的机器学习流程。\"},{\"question\":\"知识分解在知识整合机器学习中扮演什么作用？\",\"answer\":\"文中将知识分解视为通向知识整合机器学习的路径，形成由低到高的三层集成范式，以更好地平衡整体性与还原性观点。\"}]","Pathway toward Prior Knowledge-Integrated Machine Learning in Engineering | PDF",1785812035,20,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"pathway-toward-prior-knowledge-integrated-machine-learning-in-engineering","",{"@graph":35,"@context":84},[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/pathway-toward-prior-knowledge-integrated-machine-learning-in-engineering/122663/",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],{"name":71,"@type":72,"acceptedAnswer":73},"为什么在建筑工程等依赖先验知识的领域中，机器学习进展相对较慢？","Question",{"text":74,"@type":75},"文中指出，数据驱动方法在工程领域往往需要明确的领域规律与先验知识支持，而缺乏充分的数据或难以建模物理反问题时会导致性能差距与不确定性。","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"研究提出了哪些方式来整合第一性原理模型与数据驱动方法？",{"text":79,"@type":75},"研究强调在知识表征中分析信息不确定性的来源，并通过三层次的知识分解范式构建知识整合的机器学习流程。",{"name":81,"@type":72,"acceptedAnswer":82},"知识分解在知识整合机器学习中扮演什么作用？",{"text":83,"@type":75},"文中将知识分解视为通向知识整合机器学习的路径，形成由低到高的三层集成范式，以更好地平衡整体性与还原性观点。","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]