[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124117-en":3,"doc-seo-124117-105":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},124117,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Fault Prediction in Resistance Spot Welding: A Comparison of Machine Learning Approaches","Resistance spot welding is widely used in manufacturing and combines high reliability with straightforward automation. Defective-weld detection remains difficult because it typically relies on destructive methods or expensive, slow non-destructive testing such as ultrasound. Industrial robots collect contextual and process-specific data during operation, enabling data-driven prediction of faults. This study uses a dataset from a real plant labeled via ultrasonic checks to evaluate shallow and deep learning pipelines; results indicate limited predictive performance, with qualitative analysis suggesting that inherent data biases and dataset limitations restrict fault detection.","POLITECNICO DI TORINO  \nRepository ISTITUZIONALE  \nFault Prediction in Resistance Spot Welding: A Comparison of Machine Learning Approaches  \nOriginal  \nFault Prediction in Resistance Spot Welding: A Comparison of Machine Learning Approaches / Ciravegna, G. ; Galante, F. ; Giordano, D. ; Cerquitelli, T. ; Mellia, M.. -In: ELECTRONICS. -ISSN 2079-9292. -13:18(2024) .[10.3390/electronics13183693]  \nAvailability:  \nThis version is available at: 11583/2993086 since: 2024-10-04T17:18:45Z  \nPublisher:  \nMultidisciplinary Digital Publishing Institute (MDPI)  \nPublished  \nDOI:10.3390/electronics13183693  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \n(Article begins on next page)  \n17 February 2025  \n electronics   \nArticle  \nFault Prediction in Resistance Spot Welding: A Comparison of Machine Learning Approaches  \nGabriele Ciravegna *, Franco Galante *, Danilo Giordano , Tania Cerquitelli  and Marco Mellia   \nCitation: Ciravegna, G.; Galante, F.; Giordano, D.; Cerquitelli, T.; Mellia, M. Fault Prediction in Resistance Spot Welding: A Comparison of Machine Learning Approaches. Electronics 2024, 13, 3693. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)electronics13183693  \nAcademic Editor: Chunping Li  \nReceived: 6 August 2024  \nRevised: 5 September 2024  \nAccepted: 14 September 2024  \nPublished: 18 September 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \nPolitecnico di Torino, Department of Control and Computer Engineering, Corso Duca degli Abruzzi, 24,  \n10129 Torino, Italy; danilo.giordano@polito.it (D.G.); tania.cerquitelli@polito.it (T.C.); marco.mellia@polito.it (M.M.)  \n* Correspondence: gabriele.ciravegna@polito.it (G.C.); franco.galante@polito.it (F.G.)  \nAbstract: Resistance spot welding is widely adopted in manufacturing and is characterized by high reliability and simple automation in the production line. The detection of defective welds is a difficult task that requires either destructive or expensive and slow non-destructive testing (e.g., ultrasound) . The robots performing the welding automatically collect contextual and process-specific data. In this paper, we test whether these data can be used to predict defective welds. To do so, we use adataset collected in a real industrial plant that describes welding-related data labeled with ultrasonic quality checks. We use these data to develop several pipelines based on shallow and deep learning machine learning algorithms and test the performance of these pipelines in predicting defective welds. Our results show that, despite the development of different pipelines and complex models, the machine-learning-based defect detection algorithms achieve limited performance. Using a qualitative analysis of model predictions, we show that correct predictions are often a consequence of inherent biases and intrinsic limitations in the data. We therefore conclude that the automatically collected data have limitations that hamper fault detection in a running production plant.  \nKeywords: resistance spot welding; machine learning; fault prediction  \n1. Introduction  \nThe advent of Industry 4.0 has opened up unprecedented opportunities facilitating communication and collaboration between machines and processes and enabling intelligent decision making through the use of smart industrial technologies. The increasing availability of large amounts of data collected in industrial plants is paving the way for new opportunities such as the use of artificial intelligence and machine learning solutions to improve the effici","cbCaihiRhJKUPUC6","https://ap.wps.com/l/cbCaihiRhJKUPUC6","pdf",2029142,1,18,"English","en",105,"# Introduction\n## Industry 4.0 and industrial data challenges\n## Resistance spot welding process overview\n## Automatic defect detection and ML pipelines","[{\"question\":\"Why is fault prediction in resistance spot welding challenging?\",\"answer\":\"Defective welds are relatively rare due to high process reliability, and process variability introduces noise. Non-destructive quality checks such as ultrasound are costly and slow, making accurate labeling and detection difficult.\"},{\"question\":\"What data are used to build the prediction models in this study?\",\"answer\":\"The work uses a dataset collected in a real industrial plant. Welding-related variables are labeled using ultrasonic quality checks and then used to train multiple shallow and deep learning pipelines.\"},{\"question\":\"What overall performance do machine-learning approaches achieve?\",\"answer\":\"Despite testing different pipelines and complex models, the machine-learning-based defect detection reaches limited performance. Qualitative analysis indicates many correct predictions can result from inherent biases and intrinsic limitations of the dataset.\"}]","Fault Prediction in Resistance Spot Welding: A Comparison of Machine Learning Approaches | PDF",1785820518,45,{"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},"fault-prediction-in-resistance-spot-welding-a-comparison-of-machine-learning-approaches","",{"@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/fault-prediction-in-resistance-spot-welding-a-comparison-of-machine-learning-approaches/124117/",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 is fault prediction in resistance spot welding challenging?","Question",{"text":75,"@type":76},"Defective welds are relatively rare due to high process reliability, and process variability introduces noise. Non-destructive quality checks such as ultrasound are costly and slow, making accurate labeling and detection difficult.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data are used to build the prediction models in this study?",{"text":80,"@type":76},"The work uses a dataset collected in a real industrial plant. Welding-related variables are labeled using ultrasonic quality checks and then used to train multiple shallow and deep learning pipelines.",{"name":82,"@type":73,"acceptedAnswer":83},"What overall performance do machine-learning approaches achieve?",{"text":84,"@type":76},"Despite testing different pipelines and complex models, the machine-learning-based defect detection reaches limited performance. Qualitative analysis indicates many correct predictions can result from inherent biases and intrinsic limitations of the dataset.","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"]