[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128366-en":3,"doc-seo-128366-105":31,"detail-sidebar-cat-0-en-105":92},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128366,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Prediction of spatter-related defects in metal laser powder bed fusion by analytical and machine learning modelling applied to off-axis long-exposure monitoring","Laser powder bed fusion of metals relies on effective quality assurance, yet spatter-driven flaws such as lack-of-fusion porosities continue to limit industrial adoption. This study builds analytical image-processing and machine learning models to predict spatter-related defects using off-axis long-exposure imaging signatures. Layer-wise off-axis images are aligned with X-ray computed tomography cross-sections to quantify the correlation between monitored signatures and actual defects. Both methods are compared, highlighting accuracy targets and early detection potential.","Additive Manufacturing 94 (2024) 104504  \nContents lists available at ScienceDirect  \nAdditive Manufacturing  \njournal [homepage:](homepage: www.elsevier.com/locate/addma)[ www.elsevier.com/locate/addma](homepage: www.elsevier.com/locate/addma)  \n| Prediction of spatter-related defects in metal laser powder bed fusion by analytical and machine learning modelling applied to off-axis\u003Cbr>long-exposure monitoring |  |  |  |\n| --- | --- | --- | --- |\n| Nicol`o Bonato *, Filippo Zanini , Simone Carmignato\u003Cbr>Department of Management and Engineering, University of Padua, Vicenza, Italy |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Laser powder bed fusion In-process monitoring Image processing\u003Cbr>Machine learning\u003Cbr>Data correlation\u003Cbr>X-ray computed tomography |  | Laser powder bed fusion of metals is increasingly used for fabricating complex parts requiring good mechanical properties. Simultaneously, researchers in the field are intensifying the efforts to reduce defects, such as internal porosities, which hinder a wider industrial adoption of this technology, urging process monitoring to a pivotal role in defect identification and mitigation. Therefore, understanding the correlation between in-process monitoring signals and post-process actual defects is fundamental to taking informed decisions and potential corrective actions during the process. This work focuses on developing models to predict spatter-related defects from specific process signatures detected through off-axis long-exposure imaging. Layer-wise images were properly aligned with corresponding cross-sections from tomographic reconstructions to investigate the relationship between spatter-related signatures and actual defects measured by X-ray computed tomography. This relationship was used as a knowledge basis to develop an analytical image-processing approach and a machine learning-based methodology, which were then compared in terms of their correlation performances. The advantages and limitations of both methods are discussed in the paper. Both approaches led to promising results in the prediction of lack-of-fusion defects caused by spatters, with the machine learning approach showing a prediction accuracy in the order of 90 % for defects with equivalent diameter above 90 µm, while the analytical model needed equivalent diameters larger than 130 µm to reach a prediction accuracy in the order of 80 %. Furthermore, the machine learning method led to strong results regarding early defect detection, with most of the investigated defects properly predicted by analysing two consecutive layers after the signature detection. |  |\n\n1. Introduction  \nAdditive manufacturing (AM) technologies have emerged as innovative solutions for fabricating components with complex geometries for several applications, spanning industries such as biomedical, aerospace, automotive, tooling, and consumer goods [1]. In particular, laser-based powder bed fusion of metals (PBF-LB/M) offers unprecedented advantages in terms of design freedom, material buy-to-fly ratio, weight reduction, and mechanical performances. However, ensuring the stringent quality standards required across various applications remains a significant challenge, for example, due to the susceptibility of the fabricated parts to flaws, including internal porosities, which poses a considerable barrier to achieving consistent and reliable mechanical properties [2]. Despite significant efforts to optimize process parameters, the intrinsic variability in mechanical properties persists due to the  \ndifficult-to-predict nature of defects formed during PBF-LB/M fabrication [3]. Notably, lack-of-fusion voids – distinguishable by their characteristic irregular shapes and the presence of partially melted entrapped powder particles – significantly impact part resistance and often lead to fatigue failures at the material-pore interface [4]. The quest for a comprehensive understanding of the specific causes behi","cbCaiubMZXYnYfON","https://ap.wps.com/l/cbCaiubMZXYnYfON","pdf",7191420,2,1,11,"English","en",105,"# Introduction\n## In-process monitoring and defect formation\n# Methods\n## Analytical image-processing approach\n## Machine learning modelling\n# Results\n## Correlation performance and prediction accuracy\n## Early defect detection\n# Discussion","[{\"question\":\"What defect type does the study aim to predict in metal laser powder bed fusion?\",\"answer\":\"The models target spatter-related lack-of-fusion defects, which create internal porosities that can degrade mechanical performance and fatigue resistance.\"},{\"question\":\"How are off-axis long-exposure monitoring images used in the prediction workflow?\",\"answer\":\"Off-axis, layer-wise long-exposure images are aligned with corresponding X-ray computed tomography cross-sections to link process signatures with measured defects.\"},{\"question\":\"How do the analytical model and the machine learning approach compare in predictive performance?\",\"answer\":\"Both approaches show promising prediction results; the machine learning method reaches about 90% accuracy for defects above roughly 90 µm, while the analytical model needs larger equivalent diameters (above about 130 µm) to achieve around 80% accuracy.\"}]","Prediction of spatter-related defects in metal laser powder bed fusion by analytical and machine learning modelling applied to off-axis long-exposure monitoring | PDF",1785947113,28,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"prediction-of-spatter-related-defects-in-metal-laser-powder-bed-fusion-by-analytical-and-machine-learning-modelling-applied-to-off-axis-long-exposure-monitoring","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/prediction-of-spatter-related-defects-in-metal-laser-powder-bed-fusion-by-analytical-and-machine-learning-modelling-applied-to-off-axis-long-exposure-monitoring/128366/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What defect type does the study aim to predict in metal laser powder bed fusion?","Question",{"text":76,"@type":77},"The models target spatter-related lack-of-fusion defects, which create internal porosities that can degrade mechanical performance and fatigue resistance.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are off-axis long-exposure monitoring images used in the prediction workflow?",{"text":81,"@type":77},"Off-axis, layer-wise long-exposure images are aligned with corresponding X-ray computed tomography cross-sections to link process signatures with measured defects.",{"name":83,"@type":74,"acceptedAnswer":84},"How do the analytical model and the machine learning approach compare in predictive performance?",{"text":85,"@type":77},"Both approaches show promising prediction results; the machine learning method reaches about 90% accuracy for defects above roughly 90 µm, while the analytical model needs larger equivalent diameters (above about 130 µm) to achieve around 80% accuracy.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]