[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119379-en":3,"doc-seo-119379-105":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},119379,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Physics-Informed Machine Learning for Smart Additive Manufacturing","Compared with physics-based computational manufacturing, data-driven machine learning offers alternative routes to smart manufacturing, but its “black box” behavior limits interpretability of outcomes. Governing physical laws are also not effectively embedded to form data-efficient learning algorithms. This paper presents a physics-informed machine learning (PIML) model that combines neural networks with physical laws to improve accuracy, transparency, and generalization, demonstrated through case studies in laser metal deposition (LMD).","[Available online at www.sciencedirect.com](Available online at www.sciencedirect.com)  \nScienceDirect  \nProcedia CIRP 00 (2024) 000–000  \n[www.elsevier.com/locate/procedia](www.elsevier.com/locate/procedia)  \n18th CIRP Conference on Intelligent Computation in Manufacturing Engineering Physics-Informed Machine Learning for Smart Additive Manufacturing  \nRahul Sharmaa,b, Maziar Raissic, Y.B. Guoa,b *  \na Dept. of Mechanical and Aerospace Engineering, Rutgers University-New Brunswick, Piscataway, NJ 08854, USA  \nb New Jersey Advanced Manufacturing Institute, Rutgers University-New Brunswick, Piscataway, NJ 08854, USA  \nC Dept. of Mathematics, University of California, Riverside, CA 92521, USA  \n* Corresponding author. Tel.: +1-848-445-2225; fax: + [1-732-445-3124.](1-732-445-3124. E-mail address: yuebin.guo@rutgers.edu)[ E-mail address:](1-732-445-3124. E-mail address: yuebin.guo@rutgers.edu)[ yuebin.guo@rutgers.edu](1-732-445-3124. E-mail address: yuebin.guo@rutgers.edu)  \nAbstract  \nCompared to physics-based computational manufacturing, data-driven models such as machine learning (ML) are alternative approaches to achieve smart manufacturing. However, the data-driven ML’s “black box” nature has presented a challenge to interpreting its outcomes. On the other hand, governing physical laws are not effectively utilized to develop data-efficient ML algorithms. To leverage the advantages of ML and physical laws of advanced manufacturing, this paper focuses on the development of a physics-informed machine learning (PIML) model by integrating neural networks and physical laws to improve model accuracy, transparency, and generalization with case studies in laser metal deposition (LMD) .  \n© 2024 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license ([https://creativecommons.org/licenses/by-nc-nd/4.0](https://creativecommons.org/licenses/by-nc-nd/4.0))  \nPeer-review under responsibility of the scientific committee of the 18th CIRP Conference on Intelligent Computation in Manufacturing Engineering, 10-12 July, Gulf of Naples, Italy  \nKeywords: Physics-informed machine learning; Additive manufacturing; Laser metal deposition; Smart manufacturing  \n1. Introduction  \nThe recent development in artificial intelligence (AI) and machine learning (ML) technologies demonstrates significant promise for advancements in the modeling of manufacturing processes. The effectiveness of traditional data-driven ML tools in data science is mainly due to the availability of vast amounts of labeled datasets, which can be acquired through experiments or physics-based simulations. However, data ingestion is very expensive and often restricts the feasibility of data-driven ML models as surrogate models for manufacturing processes.  \nRecently, the emergence of scientific machine learning, especially physics-informed machine learning (PIML), has introduced a new paradigm that leverages deep learning for solving partial differential equations (PDE) (1) . This  \nadvancement enables the replacement of traditional numerical discretization methods, e.g., finite difference method (FDM) and finite element method (FEM), with neural networks (NNs) that can approximate PDE solutions. This framework integrates data with fundamental physical principles, such as the conservation laws of momentum, mass, and energy in laser powder bed fusion (LPBF) and laser direct energy deposition (DED), directly into the neural network architecture to guide a learning process. PIML offers an alternative to mesh-dependent methods like FDM and FEM, providing a mesh-free approach through automatic differentiation (2) . This innovative strategy has the potential to navigate the complexities associated with the curse of dimensionality. Differing from traditional deep learning frameworks, PIML models can often be developed without the necessity for training data. Furthermore, with the  \n2212-8271 © 2024 The Authors. Published by ELSEVIER B.V. This is ","cbCaidk5URLYVxrq","https://ap.wps.com/l/cbCaidk5URLYVxrq","pdf",2558552,1,6,"English","en",105,"# Abstract\n# Introduction\n# Keywords","[{\"question\":\"What problem does physics-informed machine learning address in smart additive manufacturing?\",\"answer\":\"It addresses the limited interpretability of data-driven “black box” models and the lack of effective use of governing physical laws for data-efficient learning.\"},{\"question\":\"How does the proposed PIML model integrate physical knowledge?\",\"answer\":\"It embeds fundamental physical principles, such as conservation laws, directly into the neural network architecture to guide the learning process.\"},{\"question\":\"Why is laser metal deposition (LMD) used as a case study?\",\"answer\":\"The paper demonstrates the PIML approach using LMD examples to show improvements in accuracy, transparency, and generalization for additive manufacturing.\"}]","Physics-Informed Machine Learning for Smart Additive Manufacturing | PDF",1785724012,15,{"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},"physics-informed-machine-learning-for-smart-additive-manufacturing","",{"@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/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/physics-informed-machine-learning-for-smart-additive-manufacturing/119379/",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","2026-08-03",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 problem does physics-informed machine learning address in smart additive manufacturing?","Question",{"text":75,"@type":76},"It addresses the limited interpretability of data-driven “black box” models and the lack of effective use of governing physical laws for data-efficient learning.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed PIML model integrate physical knowledge?",{"text":80,"@type":76},"It embeds fundamental physical principles, such as conservation laws, directly into the neural network architecture to guide the learning process.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is laser metal deposition (LMD) used as a case study?",{"text":84,"@type":76},"The paper demonstrates the PIML approach using LMD examples to show improvements in accuracy, transparency, and generalization for additive manufacturing.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]