[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-467242-105":59,"doc-detail-467242-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","polymer-melt-stability-monitoring-in-injection-moulding-using-lstm-based-time-series-models","Polymer Melt Stability Monitoring in Injection Moulding Using LSTM-Based Time-Series Models","","Data-driven framework enables early detection of polymer melt instability in industrial injection moulding with Long Short-Term Memory (LSTM) time-series models. The approach leverages six months of continuous production data, about 280,000 injection cycles, from a fully operational thermoplastic injection line. Since melt behaviour transitions gradually and conventional threshold monitoring misses these shifts, the model learns temporal patterns across torque, pressure, temperature, and rheology. Physically informed volatility windows provide supervised labels with sparse defect annotations, allowing instability recognition minutes before defects emerge, using standard machine signals. ",{"@graph":69,"@context":123},[70,84,106],{"@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/polymer-melt-stability-monitoring-in-injection-moulding-using-lstm-based-time-series-models/467242/",{"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/polymer-melt-stability-monitoring-in-injection-moulding-using-lstm-based-time-series-models/467242.png","ImageObject",300,407,{"name":92,"@type":93},"Blue Pony","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-09","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the proposed framework address in injection moulding?","Question",{"text":113,"@type":114},"It targets early detection of polymer melt instability, where gradual thermo-rheological changes can lead to defects before they are caught by conventional threshold monitoring.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the LSTM model improve monitoring compared with threshold-based methods?",{"text":118,"@type":114},"LSTMs learn sequential temporal dependencies across successive cycles, capturing nonlinear time-dependent relationships in torque, pressure, temperature, and rheology that static methods miss.",{"name":120,"@type":111,"acceptedAnswer":121},"How are training labels created when defect annotations are limited?",{"text":122,"@type":114},"The study uses a physically informed labelling strategy that defines volatile zones as short time windows preceding operator-identified non-conforming parts, enabling supervised learning with sparse defect labels.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},467242,1791172897,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},962090760266,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Article  \nPolymer Melt Stability Monitoring in Injection Moulding Using LSTM-Based Time-Series Models  \nPedro Costa 1, Sílvio Priem Mendes 1,2 and Paulo Loureiro 1,2, *  \nAcademic Editor: Alexey V. Lyulin  \nReceived: 2 December 2025  \nRevised: 15 December 2025  \nAccepted: 16 December 2025  \nPublished: 23 December 2025  \nCopyright: © 2025 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.  \n1 School of Technology and Management, Polytechnic University of Leiria, 2411-901 Leiria, Portugal; [2220129@my.ipleiria.pt](2220129@my.ipleiria.pt) (P.C.); [smendes@ipleiria.pt](smendes@ipleiria.pt) (S.P.M.)  \n2 Computer Science and Communication Research Centre, School of Technology and Management, Polytechnic University of Leiria, 2411-901 Leiria, Portugal  \n* [Correspondence: paulo.loureiro@ipleiria.pt](Correspondence: paulo.loureiro@ipleiria.pt)  \nAbstract  \nThis work presents a data-driven framework for early detection of polymer melt instability in industrial injection moulding using Long Short-Term Memory (LSTM) time-series models. The study uses six months of continuous production data comprising approximately 280,000 injection cycles collected from a fully operational thermoplastic injection line. Because melt behaviour evolves gradually and conventional threshold-based monitoring often fails to capture these transitions, the proposed approach models temporal patterns in torque, pressure, temperature, and rheology to identify drift conditions that precede quality degradation. A physically informed labelling strategy enables supervised learning even with sparse defect annotations by defining volatile zones as short time windows preceding operator-identified non-conforming parts, allowing the model to recognise instability windows minutes before defects emerge. The framework is designed for deployment on standard machine signals without requiring additional sensors, supporting proactive process adjustments, improved stability, and reduced scrap in injection moulding environments. These findings demonstrate the potential of temporal deep-learning models to enhance real-time monitoring and contribute to more robust and adaptive manufacturing operations.  \nKeywords: defect prediction; LSTM; injection moulding; real production data; data-driven solution  \n1. Introduction  \nInjection moulding is one of the most widely used manufacturing processes for producing thermoplastic parts, especially in high-volume sectors such as automotive, consumer goods, and medical devices. Although the process is robust and largely repeatable, the quality of moulded components is highly sensitive to the thermo-rheological behaviour of the polymer melt. Small variations in melt temperature, shear rate, or residence time can alter viscosity and flow dynamics, potentially leading to defects such as short shots, warpage, sink marks, weld-line weakness, or incomplete filling. Because these deviations often evolve gradually over several cycles, early detection is essential for preventing drift toward unstable operating conditions.  \nConventional process-monitoring systems typically rely on predefined thresholds or rule-based logic. While effective for detecting abrupt failures, such static approaches are unable to capture the nonlinear and time-dependent relationships that characterise melt behaviour. Minor shifts in torque, pressure, or thermal load may precede visible defects by several minutes, yet remain undetected by threshold-based models. This has motivated  \nthe adoption of machine-learning (ML) approaches capable of learning complex patterns directly from sensor data.  \nRecent research has explored unsupervised anomaly detection, autoencoder-based reconstruction, and generative modelling for identifying deviations in injection moulding processes. However, many existing approaches treat cycle data as independent observation","cbCaiswDO3UvgcjL","https://ap.wps.com/l/cbCaiswDO3UvgcjL","pdf",332247,14,"English","# Abstract\n# Keywords\n# Introduction\n## Injection moulding quality sensitivity and need for early detection\n## Limits of threshold-based monitoring and motivation for ML\n## Related work and research gap\n## LSTM-based temporal modelling approach\n## Research gap and main contributions","[{\"question\":\"What problem does the proposed framework address in injection moulding?\",\"answer\":\"It targets early detection of polymer melt instability, where gradual thermo-rheological changes can lead to defects before they are caught by conventional threshold monitoring.\"},{\"question\":\"How does the LSTM model improve monitoring compared with threshold-based methods?\",\"answer\":\"LSTMs learn sequential temporal dependencies across successive cycles, capturing nonlinear time-dependent relationships in torque, pressure, temperature, and rheology that static methods miss.\"},{\"question\":\"How are training labels created when defect annotations are limited?\",\"answer\":\"The study uses a physically informed labelling strategy that defines volatile zones as short time windows preceding operator-identified non-conforming parts, enabling supervised learning with sparse defect labels.\"}]","Polymer Melt Stability Monitoring in Injection Moulding Using LSTM-Based Time-Series Models | PDF",1790772547,35,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/abf5b1230d6c45423db5c42c5189be25.webp",983,1390,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/95f1113342e509dad8f977f9628daef7.webp",982,1388,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/a0879bcf25afb7c6b4c69ab2b98eb8bb.webp",981,1387,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/27c85f70ce40c082803a98f7f59aaa2a.webp",980,1385]