[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291194-105":59,"doc-detail-291194-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","quality-monitoring-of-projection-welding-using-machine-learning-with-small-data-sets","Quality monitoring of projection welding using machine learning with small data sets","","This document presents a quality monitoring approach for capacitor discharge projection welding using machine learning under limited data availability. It contrasts expert-system evaluation, which is time-consuming and task-specific, with machine learning that requires labeled experiments. The work investigates semi-supervised learning to reduce the number of classified weld training samples needed for reliable prediction, using evaluated process time signals as inputs. Results report 389 classified weld tests and training-data reduction to 31 classified data sets.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/quality-monitoring-of-projection-welding-using-machine-learning-with-small-data-sets/291194/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/quality-monitoring-of-projection-welding-using-machine-learning-with-small-data-sets/291194.png","ImageObject",300,407,{"name":92,"@type":93},"Valentina","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-18","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is real-time quality monitoring needed for capacitor discharge projection welding?","Question",{"text":112,"@type":113},"Capacitor discharge welding is an efficient but uncontrolled process, and ensuring joint quality requires monitoring. Real-time monitoring supports reliable quality assurance compared with purely empirical evaluations.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What limitation affects machine-learning quality prediction for this welding process?",{"text":117,"@type":113},"High prediction probability typically requires classified welding experiments, but in industrial manufacturing it is rarely feasible to generate large amounts of such labeled data.",{"name":119,"@type":110,"acceptedAnswer":120},"How does semi-supervised learning help in this study?",{"text":121,"@type":113},"Semi-supervised learning is used to enable model development on small data sets, reducing the amount of training data required compared with supervised learning baselines.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},291194,1789643655,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":56,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":143,"preview_page_count":4},13056703020460,"https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923","Dieses Dokument ist eine Zweitveröffentlichung (Postprint) / This is a self-archiving document (accepted version):  \nJohannes Koal, Tim Hertzschuch, Jörg Zschetzsche, Uwe Füssel  \nQuality monitoring of projection welding using machine learning with small data sets  \nErstveröffentlichung in / First published in:  \nScience and Technology of Welding and Joining.2023. 28(4) . SAGE Publications. ISSN: 1362-1718 .  \nDOI: [https://doi.org/10.1080/13621718.2022.2162709](https://doi.org/10.1080/13621718.2022.2162709)  \nDiese Version ist verfügbar / This version is available on:  \n[https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-889922](https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-889922)  \nDieses Werk ist lizenziert unter einer Creative Commons Namensnennung-Weitergabe unter gleichen Bedingungen 4 .0 International Lizenz.  \nThis work is licensed under a Creative Commons Attribution-ShareAlike 4 .0 International License.  \nFinal edited version was published in Science and Technology of Welding and Joining. 2023. 28(4).. SAGE Publications.  \nISSN: 1362‑1718.  \n[https://doi.org/10.1080/13621718.2022.2162709](https://doi.org/10.1080/13621718.2022.2162709)  \nQuality monitoring of projection welding using machine learning with  \nsmall data sets  \nJohannes Koala* and Tim Hertzschucha** and Martin Baumgartena and Jörg  \nZschetzschea and Uwe Füssela  \na Technische Universität Dresden, Institute of Manufacturing Science and Engineering,  \nChair of Joining Technology and Assembly, Dresden, Germany  \n* Johannes Koal, johannes.koal@tu-dresden.de, ORCID: 0000-0003-0763-552X  \n** Tim Hertzschuch, tim.hertzschuch@tu-dresden.de, ORCID: 0000-0001-5030-0819  \n3  \nProvided by Sächsische Landesbibliothek, Staats ‑ und Universitätsbibliothek Dresden  \nFinal edited version was published in Science and Technology of Welding and Joining. 2023. 28(4).. SAGE Publications.  \nISSN: 1362‑1718.  \n[https://doi.org/10.1080/13621718.2022.2162709](https://doi.org/10.1080/13621718.2022.2162709)  \nQuality monitoring of projection welding using machine learning with  \nsmall amounts of data  \nCapacitor discharge welding is an efficient, cost-effective and stable process. It is  \nmostly used for projection welding. Real-time monitoring is desired to ensure  \nquality. Until this point, measured process quantities were evaluated through  \nexpert systems. This method takes much time for developing, is strongly  \nrestricted to specific welding tasks and needs deep understanding of the process.  \nAnother possibility is quality prediction based on process data with machine  \nlearning. This method can overcome the downsides of expert systems. But it  \nrequires classified welding experiments to achieve a high prediction probability.  \nIn industrial manufacturing, it is rarely possible to generate big sets of this type  \nof data. Therefore, semi-supervised learning will be investigated to enable model  \ndevelopment on small data sets. Supervised learning is used to develop machine  \nlearning models on large amounts of data. These models are used as a  \ncomparison to the semi-supervised models. The time signals of the process  \nparameters are evaluated in these investigations. A total of 389 classified weld  \ntests were performed. With semi-supervised learning methods, the amount of  \ntraining data necessary was reduced to 31 classified data sets  \nKeywords: resistance welding; capacitor discharge welding; projection welding;  \nmachine learning; supervised learning; semi-supervised learning, process  \nmonitoring  \n4  \nProvided by Sächsische Landesbibliothek, Staats ‑ und Universitätsbibliothek Dresden  \nFinal edited version was published in Science and Technology of Welding and Joining. 2023. 28(4).. SAGE Publications.  \nISSN: 1362‑1718.  \n[https://doi.org/10.1080/13621718.2022.2162709](https://doi.org/10.1080/13621718.2022.2162709)  \nIntroduction  \nCapacitor discharge welding (CD welding) is mostly used for welding rotationally  \nsymmetrical components. Finished components","cbCaik39I2Youfbo","https://ap.wps.com/l/cbCaik39I2Youfbo","pdf",1097407,"English","# Introduction\n## Problem background and need for monitoring\n## Limits of current evaluation methods and data scarcity\n# Semi-supervised learning approach\n## Rationale compared with supervised learning","[{\"question\":\"Why is real-time quality monitoring needed for capacitor discharge projection welding?\",\"answer\":\"Capacitor discharge welding is an efficient but uncontrolled process, and ensuring joint quality requires monitoring. Real-time monitoring supports reliable quality assurance compared with purely empirical evaluations.\"},{\"question\":\"What limitation affects machine-learning quality prediction for this welding process?\",\"answer\":\"High prediction probability typically requires classified welding experiments, but in industrial manufacturing it is rarely feasible to generate large amounts of such labeled data.\"},{\"question\":\"How does semi-supervised learning help in this study?\",\"answer\":\"Semi-supervised learning is used to enable model development on small data sets, reducing the amount of training data required compared with supervised learning baselines.\"}]","Quality monitoring of projection welding using machine learning with small data sets | PDF",48]