[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122127-en":3,"doc-seo-122127-105":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},122127,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning models to forecast defects occurrence on foundry products","Manufacturing defects increase production cost and environmental burden, especially in energy-intensive metallurgical processes. In the cast iron foundry sector, defect formation depends on raw material quality, melting conditions, cast iron final temperature, ferroalloy additions, and final composition, making it multifactorial and often rare. The paper proposes machine-learning models that predict and classify defects on foundry production lines. Decision-tree-based methods, enhanced with data augmentation for unbalanced defect datasets, deliver efficient models with encouraging performance, supporting operators in managing processes and stopping production when adjustments are not feasible.","[Available online at www.sciencedirect.com](Available online at www.sciencedirect.com)  \nScienceDirect  \nIFAC PapersOnLine 58-22 (2024) 113–118  \nMachine Learning models to forecast defects occurrence on foundry products  \nS. Dettori*, A. Zaccara**, L. Laid*, I. Matino*, M. Vannucci*, V. Colla*, G. Bontempi***, L. Forlani***  \n*TeCIP Institute, Scuola Superiore Sant’Anna, Pisa, Italy (e-mail: {s.dettori, a.zaccara, l.laid, m.vannucci, [v.colla}@santannapisa.it](v.colla}@santannapisa.it)).  \n**Dipartimento di Ingegneria Industriale, Università di Padova, Padova,(Italy),  \n***Fonderia di Torbole S.r.l, Torbole Casaglia, Italy (e-mail: {g.bontempi, l.forlani}@fonderiaditorbole.it)  \nAbstract: Manufacturing defects negatively affect production cost and environmental impact. This impact is even heavier for production processes that are particularly energy intensive, such as in the metallurgical industry. In the cast iron foundry sector, components manufacturing can be affected by various defects that depend on quality of raw materials fed to the melting process, process parameters, cast iron final temperature, ferroalloys additions and final composition. Defects formation is a multifactorial phenomenon, for which relevant factors are not easy to identify, as it is also a rare event. This paper presentsa set of models based on machine learning methodologies for predicting and classifying defects on foundry production lines to assist process operators in managing the process and, eventually, stop production when it is not possible to adjust process parameters. The modelling phase exploits decision trees methodologies enhanced with algorithms for augmenting unbalanced datasets related to defects occurrences. The combination of these methodologies produces efficient models showing very encouraging results.  \nCopyright © 2024 The Authors. 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/))  \nKeywords: Machine Learning, ML, cast iron foundry, manufacturing defects prediction, anomalies, decision tree, unbalanced datasets, data augmentation.  \n1. INTRODUCTION  \nMaintaining a high-quality final product while ensuring compliance with increasingly stringent environmental constraints and cost sustainability is one of the most relevant current challenges for the process and manufacturing industry. The role of foundries is crucial: they are the main source of castings and produce indispensable components for other industries. The presence of defects in final products has a negative impact on a foundry's profits. Production defects often result in reworking costs, additional energy consumption, or casting waste generation. Defects can also be discovered at later stages, such as machining, assembly or, even worse, during product use, with increased risks or rejection and complaints from customers and costs for foundries (Pribulová, Bartošová and Baricová, 2013) .  \nIn the past decades, several works were conducted to prevent defect generation. Defect identification, characterization and classification were explored in different papers. Sütőová and Grzinčič take an in-depth look at the casting defect classification and cataloguing system, a fundamental tool in the organization of a foundry. The authors propose an example of a catalogue, which classifies and describes the defects in an aluminum foundry and its advantages in supporting production and quality control operators. (Sütőová and Grzinčič, 2013) Juriani provides a detailed overview of critical casting defects and their causes, also focusing on technically feasible remedies to minimize various casting defects and improve casting quality (Juriani, 2015) . The topic of defect identification and classification is explored also using Artificial Intelligence (AI)  \nmethodologies as reported in the work of Pastor-López et al., who propose a technique for the detection of surface def","cbCaibjE6V6gdejA","https://ap.wps.com/l/cbCaibjE6V6gdejA","pdf",604523,1,6,"English","en",105,"# Abstract\n# Keywords\n# Introduction","[{\"question\":\"Why are defects in cast iron foundry manufacturing difficult to manage?\",\"answer\":\"Defects are multifactorial, driven by variables such as raw material quality, process parameters, final temperature, ferroalloy additions, and final composition. Some defects are also rare events, which makes identification and forecasting challenging.\"},{\"question\":\"What approach does the paper use to forecast and classify defects?\",\"answer\":\"It presents machine-learning models for predicting and classifying defects on foundry production lines, using decision-tree methodologies enhanced with techniques for augmenting unbalanced datasets related to defect occurrences.\"},{\"question\":\"How do the proposed models support production operators?\",\"answer\":\"They help operators manage the process and potentially stop production when it is not possible to adjust process parameters, reducing the impact of defects on cost and environmental footprint.\"}]","Machine Learning models to forecast defects occurrence on foundry products | PDF",1785808946,15,{"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},"machine-learning-models-to-forecast-defects-occurrence-on-foundry-products","",{"@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/machine-learning-models-to-forecast-defects-occurrence-on-foundry-products/122127/",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","2026-08-04",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},"Why are defects in cast iron foundry manufacturing difficult to manage?","Question",{"text":75,"@type":76},"Defects are multifactorial, driven by variables such as raw material quality, process parameters, final temperature, ferroalloy additions, and final composition. Some defects are also rare events, which makes identification and forecasting challenging.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What approach does the paper use to forecast and classify defects?",{"text":80,"@type":76},"It presents machine-learning models for predicting and classifying defects on foundry production lines, using decision-tree methodologies enhanced with techniques for augmenting unbalanced datasets related to defect occurrences.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the proposed models support production operators?",{"text":84,"@type":76},"They help operators manage the process and potentially stop production when it is not possible to adjust process parameters, reducing the impact of defects on cost and environmental footprint.","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"]