{"id":393879,"date":"2026-04-15T18:55:09","date_gmt":"2026-04-15T18:55:09","guid":{"rendered":"https:\/\/www.newsbeep.com\/il\/393879\/"},"modified":"2026-04-15T18:55:09","modified_gmt":"2026-04-15T18:55:09","slug":"ai-powered-surrogate-models-advance-real-time-simulation-for-composites-manufacturing","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/il\/393879\/","title":{"rendered":"AI-powered surrogate models advance real-time simulation for composites manufacturing"},"content":{"rendered":"<p><img decoding=\"async\" loading=\"lazy\" alt=\"IMDEA \" data-height=\"229\" data-width=\"343\" src=\"https:\/\/www.newsbeep.com\/il\/wp-content\/uploads\/2026\/04\/0426-cw-news-imdea.jpg;maxWidth=385.jpeg\" width=\"343px\" height=\"229px\"\/><\/p>\n<p data-track-changes-ignore=\"ignore\">Source | IMDEA<\/p>\n<p>Recently published research from\u00a0<a href=\"https:\/\/www.compositesworld.com\/suppliers\/imdea-materials\" rel=\"nofollow noopener\" target=\"_blank\">IMDEA Materials Institute<\/a>\u00a0(Madrid, Spain) and the Technical University of Madrid (UPM) aims to advance real-time simulation capabilities for composite manufacturing processes.<\/p>\n<p>The study, \u201cA deep surrogate model for filling simulations in liquid composite moulding on unstructured 3D grids,\u201d is co-authored by Prof. Carlos Gonz\u00e1lez, Dr. Davide Mocerino and\u00a0predoctoral researcher Sofia Fern\u00e1ndez Le\u00f3n from IMDEA Materials, and the UPM\u2019s Profs. Roberto Valle Fern\u00e1ndez and Luis Baumela.<\/p>\n<p>The researchers say their research addresses key limitations of current deep learning surrogate\u00a0models for simulating fluid flow in composite manufacturing processes, and the\u00a0 results\u00a0highlight the potential of data-driven approaches to enhance efficiency, adaptability\u00a0and resilience in advanced manufacturing processes.<\/p>\n<p>According to the researchers, liquid composite molding (LCM) simulations are essential for optimizing manufacturing processes and reducing defects such as void formation. However, their high computational cost has traditionally limited their use in real-time applications.\u00a0This research addresses that challenge by introducing a deep learning-based surrogate modeling framework capable of delivering accurate predictions in milliseconds, unlocking new possibilities for digital twins and adaptive process control.<\/p>\n<p>\u201cA key innovation here lies in overcoming one of the main bottlenecks in this field by achieving computational efficiency, high accuracy\u00a0and robustness to the irregular and unstructured\u00a0meshes commonly found in industrial settings,\u201d explains Fern\u00e1ndez Le\u00f3n. \u201cThese requirements are rarely satisfied simultaneously by existing neural network approaches.\u201d<\/p>\n<p>The researchers also introduced a multi-branched encoder-decoder architecture to model complex geometries, such as T-shaped stringers, by breaking them down into planar regions and ensuring consistency across interfaces.<\/p>\n<p>In parallel, \u201cThe proposed grid mapping technique enables the use of convolutional neural networks on unstructured 3D domains, preserving accuracy while extending applicability to realistic manufacturing scenarios,\u201d adds Fern\u00e1ndez Le\u00f3n.<\/p>\n<p>The resulting surrogate models are said to demonstrate strong agreement with both high-fidelity simulations and experimental data, while achieving speed-ups of four to five orders of magnitude compared to conventional methods. This level of performance aims to enable real-time deployment in digital manufacturing\u00a0environments, supporting more efficient, adaptive\u00a0and resilient composite production processes.<\/p>\n<p>\u201cThis study highlights the transformative potential of combining advanced manufacturing with artificial intelligence, paving the way towards fully integrated, data-driven production systems,\u201d says Fern\u00e1ndez Le\u00f3n.<\/p>\n","protected":false},"excerpt":{"rendered":"Source | IMDEA Recently published research from\u00a0IMDEA Materials Institute\u00a0(Madrid, Spain) and the Technical University of Madrid (UPM) aims&hellip;\n","protected":false},"author":2,"featured_media":393880,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[85,46,125],"class_list":{"0":"post-393879","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-technology","8":"tag-il","9":"tag-israel","10":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/393879","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/comments?post=393879"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/393879\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media\/393880"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media?parent=393879"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/categories?post=393879"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/tags?post=393879"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}