[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120142-en":3,"doc-seo-120142-105":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":20,"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},120142,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Accurate predictions of keyhole depths using machine learning-aided simulations","The keyhole phenomenon plays a central role in laser materials processing, driving defects such as pores that degrade the mechanical performance of welded, remelted, cladded, drilled, and additively manufactured components. Pore formation is linked to the dynamic behavior of the keyhole, yet accurate prediction of keyhole depth versus time remains difficult. Real-time measurements using synchrotron X-ray are costly and limited, while current simulations lack real-time laser absorptance, reducing depth accuracy. A machine learning-aided simulation approach enables accurate depth prediction across broad parameters, achieving about 10% error for titanium and aluminum alloys, outperforming existing models (50–200% error).","Title  \nAccurate predictions of keyhole depths using machine learning-aided  \nsimulations  \nAuthors  \nJiahui Zhang 1, Runbo Jiang2, Kangming Li 1, Pengyu Chen 1, Xiao Shang 1, Zhiying Liu 1, Jason Hattrick-Simpers1, Brian J. Simonds3, Qianglong Wei4, Hongze Wang4, Tao Sun5, Anthony D. Rollett6, Yu Zou 1,*  \nAffiliations  \n1Department of Materials Science and Engineering, University of Toronto, Toronto, ON M5S 3E4, Canada  \n2Advanced Light Source (ALS) Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA  \n3Applied Physics Division, Physical Measurements Laboratory, National Institute of Standards and Technology, Boulder, CO 80305, USA  \n4 School of Materials Science & Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China  \n5Department of Mechanical Engineering, Northwestern University, Evanston, IL 60208, USA 6Department of Materials Science and Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA  \n*[Corresponding author. Email: mse.zou@utoronto.ca](Corresponding author. Email: mse.zou@utoronto.ca) (Y. Z.)  \nAbstract  \nThe keyhole phenomenon is widely observed in laser materials processing, including laser welding, remelting, cladding, drilling, and additive manufacturing. Keyhole-induced defects, primarily pores, dramatically affect the performance of final products, impeding the broad use of these laserbased technologies. The formation of these pores is typically associated with the dynamic behavior of the keyhole. So far, the accurate characterization and prediction of keyhole features, particularly keyhole depth, as a function of time has been a challenging task. In situ characterization of keyhole dynamic behavior using a synchrotron X-ray is complicated and expensive. Current simulations are hindered by their poor accuracies in predicting keyhole depths due to the lack of real-time laser absorptance data. Here, we develop a machine learning-aided simulation method that allows us to accurately predict keyhole depth over a wide range of processing parameters. Based on titanium and aluminum alloys, two commonly used engineering materials as examples, we achieve an accuracy with an error margin of 10 %, surpassing those simulated using other existing models (with an error margin in a range of 50-200 %) . Our machine learning-aided simulation method is affordable and readily deployable for a large variety of materials, opening new doors to eliminate or reduce defects for a wide range of laser materials processing techniques.  \nIntroduction  \nFor over half a century, laser materials processing has been broadly used in our society, including aerospace, automotive, energy, medical, and many other high-tech industries 1, 2. Defects such aspores formed during laser-material interaction, however, pose a serious threat to the mechanical durability, reliability, and security of these components. For example, the fatigue resistance of a component is significantly decreased due to these defects 3, 4. Keyhole – a deep and narrow cavity caused by the recoil pressure generated by rapid evaporation – plays a pivotal role in generating defects during the laser materials processing processes5. The fluctuation and collapse of keyholes typically form bubbles in melts and eventually pores in final products 6, 7. Yet, the characterization and prediction of keyhole dynamics during laser-material interaction remains a technical challenge because it is a highly localized and ultra-fast process. Recent advancements in high-speed synchrotron X-ray imaging experiments 8, 9 provided insights into keyhole instability under various processing parameters of powers (P) and scan speeds (v) 10, 11 . However, their widespread adoption has been largely impeded by sophisticated instruments and limited access to synchrotron facilities. Hence, there is a compelling need for a low-cost and readily deployable solution to quantify keyhole features for a large variety of processing parameters and materials.  \nNumerical","cbCaiirSncslE2n0","https://ap.wps.com/l/cbCaiirSncslE2n0","pdf",1799390,1,28,"English","en",105,"# Introduction\n## Keyhole phenomenon and defect impact\n## Challenges in in-situ characterization\n## Limits of numerical simulation\n## Role of laser absorptance\n## Machine learning potential","[{\"question\":\"Why is predicting keyhole depth during laser processing challenging?\",\"answer\":\"Keyhole dynamics occur in a highly localized and ultra-fast process. Accurate depth prediction is also hindered because simulations lack real-time laser absorptance data.\"},{\"question\":\"What defects are associated with keyhole-induced behavior?\",\"answer\":\"Keyhole-induced defects primarily include pores. Their formation strongly affects the performance of final products.\"},{\"question\":\"How does the proposed machine learning-aided simulation method improve prediction accuracy?\",\"answer\":\"It incorporates a machine learning approach to enable accurate prediction of keyhole depth across a wide range of processing parameters, achieving roughly 10% error for titanium and aluminum alloys.\"}]","Accurate predictions of keyhole depths using machine learning-aided simulations | PDF",1785728413,71,{"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},"accurate-predictions-of-keyhole-depths-using-machine-learning-aided-simulations","",{"@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/accurate-predictions-of-keyhole-depths-using-machine-learning-aided-simulations/120142/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is predicting keyhole depth during laser processing challenging?","Question",{"text":75,"@type":76},"Keyhole dynamics occur in a highly localized and ultra-fast process. Accurate depth prediction is also hindered because simulations lack real-time laser absorptance data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What defects are associated with keyhole-induced behavior?",{"text":80,"@type":76},"Keyhole-induced defects primarily include pores. Their formation strongly affects the performance of final products.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed machine learning-aided simulation method improve prediction accuracy?",{"text":84,"@type":76},"It incorporates a machine learning approach to enable accurate prediction of keyhole depth across a wide range of processing parameters, achieving roughly 10% error for titanium and aluminum alloys.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},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"]