[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128579-en":3,"doc-seo-128579-105":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},128579,549768064778,"Finn","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine learning-assisted extreme value statistics of anomalies in AlSi10Mg manufactured by L-PBF for robust fatigue strength predictions","Traditional Extreme Value Statistics applied to block maxima sampled anomalies from Laser-Powder Bed Fusion components can lead to inaccurate characteristic defect estimates, especially when multiple defect types coexist and alter fitted maxima distributions across sampling volumes. This study applies supervised machine learning to classify defects prior to estimating maxima distributions for each defect type. The ML-assisted extreme value statistics produce maxima distributions independent of sampling volume, yielding robust exceedance curves and, via the Shiozawa curve, robust fatigue strength predictions.","Materials & Design 235 (2023) 112392  \nContents lists available at ScienceDirect  \nMaterials & Design  \njournal [homepage:](homepage: www.elsevier.com/locate/matdes)[ www.elsevier.com/locate/matdes](homepage: www.elsevier.com/locate/matdes)  \n| Machine learning-assisted extreme value statistics of anomalies in AlSi10Mg manufactured by L-PBF for robust fatigue strength predictions G. Minerva a, M. Awd b, J. Tenkampb, F. Waltherb, S. Beretta a,∗ |  |  |  |\n| --- | --- | --- | --- |\n| a Politecnico di Milano, Department of Mechanical Engineering, via La Masa 1, 20156, Milano, Italy\u003Cbr>b Technische Universität Dortmund, Chair of Materials Test Engineering, Baroper Straße 303, 44227, Dortmund, Germany |  |  |  |\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\u003Cbr>Extreme value statistics\u003Cbr>Machine learning\u003Cbr>X-ray computed tomography\u003Cbr>Fatigue |  | Traditional Extreme Value Statistics (EVS) applied to block maxima sampled anomalies of components produced by Laser-Powder Bed Fusion may produce important inaccuracies in the estimated characteristic defects. In fact, the typical presence of multiple defect types may significantly affect the fitted maxima distributions obtained from different sampling volumes. In this work, we show how the limitations of traditional EVS can be overcome by applying supervised machine learning (ML) algorithms to classify the defects before estimating the maxima distributions for each defect type. The ML-assisted EVS provided maxima distributions unaffected by the different sampling volumes. The obtained maxima distribution lead to robust estimates of exceedance curves and finally, by employing the Shiozawa curve, to robust fatigue strength predictions. |  |\n\n1. Introduction  \nFatigue behavior of additively manufactured (AMed) components has been an important research topic for several years. Many studies showed the relationship between fatigue properties and typical Additive Manufacturing (AM) features, in particular for surface roughness and internal defects. Yadollahi and Shamsaei [1] provided an overview on the effect of defect and surface roughness on the fatigue strength of AM materials. Masuo et al. [2] evaluated the effect of Hot Isostatic Pressing (HIP) and polishing on the fatigue life of Ti6Al4V, by investigating the change in surface roughness and internal defect size. Pegueset al. [3] investigated the surface roughness and size effect on the fatigue life of Ti6Al4V. Barricelli et al. [4] improved the estimates of fatigue life of annealed Ti6Al4V by accounting for shielding effect and amore accurate measurement of surface roughness. Beretta et al. [5] correlated surface roughness and the size of defects at the origin of fracture for as-built AlSi10Mg. Lee at al. [6] investigated the variability of surface roughness across different locations on the build platform and its effect on fatigue behavior for an L-PBF 316L stainless steel. Sanaei and Fatemi [7] provided a comprehensive review on the effect of volumetric defects on fatigue behavior. Romano et al. [8] described the effect of the size of artificial and natural defects on fatigue strength of AlSi10Mg. Nezhadfar et al. [9] compared fatigue behavior for different Al-based alloys, quantifying the defects size at the origin of fracture. Teschke et al.  \n* Corresponding author.  \nE-mail address: [stefano.beretta@polimi.it](stefano.beretta@polimi.it) (S. Beretta).  \n[10] validated a defect-based fatigue modeling on a titanium aluminide alloy, studying the defects at the origin of fracture. Sausto et al. [11] investigated the effect of defect type and size on the axial and torsional fatigue life of AlSi10Mg. The main conclusion is that also for AM materials a direct link exists between the maximum defect and fatigue life [12–14], which can be described by the well-known KitagawaTakahashi diagram [15]. In recent years, Machine Learning (ML) has also been successfully employed to investigate the influence of fault character","cbCaidzy1nINnAE2","https://ap.wps.com/l/cbCaidzy1nINnAE2","pdf",4136196,4,1,14,"English","en",105,"# Introduction\n## Background on fatigue in additively manufactured components\n## Role of defects and surface roughness\n## Kitagawa–Takahashi diagram and extreme defect identification\n## Motivation for machine learning in fatigue modelling","[{\"question\":\"Why can traditional extreme value statistics be inaccurate for L-PBF components?\",\"answer\":\"When components contain multiple defect types, fitted maxima distributions depend strongly on the sampling volumes, which can distort characteristic defect estimates.\"},{\"question\":\"How does the proposed method improve extreme value statistics?\",\"answer\":\"Supervised machine learning classifies defects before estimating maxima distributions separately for each defect type, producing maxima distributions unaffected by sampling volume.\"},{\"question\":\"How are robust fatigue strength predictions obtained?\",\"answer\":\"The method uses the resulting maxima distributions to derive robust exceedance curves and then applies the Shiozawa curve to predict fatigue strength.\"}]","Machine learning-assisted extreme value statistics of anomalies in AlSi10Mg manufactured by L-PBF for robust fatigue strength predictions | PDF",1786001915,35,{"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},"machine-learning-assisted-extreme-value-statistics-of-anomalies-in-alsi10mg-manufactured-by-l-pbf-for-robust-fatigue-strength-predictions","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/machine-learning-assisted-extreme-value-statistics-of-anomalies-in-alsi10mg-manufactured-by-l-pbf-for-robust-fatigue-strength-predictions/128579/",{"url":53,"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","2026-08-06",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},"Why can traditional extreme value statistics be inaccurate for L-PBF components?","Question",{"text":76,"@type":77},"When components contain multiple defect types, fitted maxima distributions depend strongly on the sampling volumes, which can distort characteristic defect estimates.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed method improve extreme value statistics?",{"text":81,"@type":77},"Supervised machine learning classifies defects before estimating maxima distributions separately for each defect type, producing maxima distributions unaffected by sampling volume.",{"name":83,"@type":74,"acceptedAnswer":84},"How are robust fatigue strength predictions obtained?",{"text":85,"@type":77},"The method uses the resulting maxima distributions to derive robust exceedance curves and then applies the Shiozawa curve to predict fatigue strength.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"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":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"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"]