[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-128823-105":59,"doc-detail-128823-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","a-machine-learning-approach-to-transferable-loss-in-weight-feeder-mass-flow-prediction-abstract","A Machine Learning approach to transferable Loss-in-Weight feeder mass flow prediction - abstract","","A machine learning framework predicts transferable Loss-in-Weight feeder mass flow performance equation parameters from material and equipment properties using three ML models. The dataset covers 50 materials and material grades and two feeders with multiple screws per feeder. One model predicts feed factor magnitude, a second predicts decay behaviour range with strong performance, and a third refines the decay range to a scalar despite variability. The method supports equipment pre-selection for feeder-screw combinations.",{"@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/a-machine-learning-approach-to-transferable-loss-in-weight-feeder-mass-flow-prediction-abstract/128823/",{"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/a-machine-learning-approach-to-transferable-loss-in-weight-feeder-mass-flow-prediction-abstract/128823.png","ImageObject",300,407,{"name":92,"@type":93},"Maeve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-18","2026-08-06",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 document address for Loss-in-Weight feeders?","Question",{"text":113,"@type":114},"It addresses predicting feeder mass flow performance parameters under varying material and equipment properties, enabling transferable modelling across different materials and feeder-screw combinations.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How many machine learning models are used, and what does each do?",{"text":118,"@type":114},"Three ML models are used: one predicts feed factor magnitude, another predicts the decay behaviour range, and a final model refines the decay range to a scalar value.",{"name":120,"@type":111,"acceptedAnswer":121},"How does the approach help in pharmaceutical manufacturing planning?",{"text":122,"@type":114},"It can be used for equipment pre-selection to determine which feeder-screw combination is likely to deliver the required mass flow.","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},128823,1786003700,{"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":130,"read_time":145},2336474466712,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","A Machine Learning approach to transferable Loss-in-Weight feeder mass flow prediction.  \nCarlota Mendez Torrecillas 1, Hikaru G. Jolliffe 1, Richard Elkes2, Gavin Reynolds3, Magdalini Aroniada2, Andrew Shier2,4, Hugh Verrier4, Sara Fathollahi5 and John Robertson 1.  \n1CMAC, 99 George Street, Glasgow, G1 1RD, United Kingdom.  \n2GSK Ware R&D, Harris’s Lane, Ware, Hertfordshire, SG12 0GX, United Kingdom.  \n3Sustainable Innovation & Transformational Excellence (xSITE), Pharmaceutical Technology & Development, Operations, AstraZeneca, Macclesfield, SK10 2NA, United Kingdom.  \n4Pfizer Research and Development UK Ltd, Ramsgate Road, Sandwich CT13 9NJ, United Kingdom 5DFE Pharma GmbH & Co. KG, Kleverstrasse 187, 47568 Goch, Germany.  \nABSTRACT  \nThe present work presents a model structure to predict Loss-in-Weight feeder mass flow performance equation parameters from material and equipment properties via three Machine Learning (ML) models; the dataset represents 50 materials and material grades and two feeders (with multiple screws per feeder) . One ML model is used for feed factor (mass/screw revolution) magnitude prediction, another for the range of feed factor decay behaviour, and a final ML model for refinement of the range to a scalar value. Feed factor magnitude is accurately predicted (test R2 of 0 .94, reducing to 0.84 when inputse.g. material properties are missing) and decay behaviour range is predicted with good accuracy (weighted F1 score of 86.4 %, and 78.6 % with missing inputs), while decay scalar refinement is challenging due to inherent variability. The present approach can be used for equipment pre-selection to determine which feeder-screw combination will likely deliver the mass flow required.  \nKeywords: feeder, modelling, Machine Learning, powders.  \n INTRODUCTION  \nOver the past decades, the pharmaceutical industry has made an enormous amount of effort to address the technical difficulties of introducing continuous manufacturing and digitalise their processes (Litsterand Bogle, 2019) . Encouraged by regulatory agencies, to avoid poor product quality and drug shortages (Lee et al., 2015; Plumb, 2005), the industry has tried to be more agile and robust by improving process understanding and developing integrated digitized frameworks [i.e.](i.e. digital)[ digital](i.e. digital) twins (Arden et al., 2021; Pickles et al., 2024; Z. Wang et al., 2017) . However, these models are required to be dynamic. They need to be able to respond to common day-to-day challenges such as the impact of excipient variability (Janssen et al., 2023; Schaber et al., 2011) or the effect of the required capacity of the line due to changing demand (Arden et al., 2021; Prostredny et al., 2024) . Ensuring a data-rich environment facilitates early execution of validation activities and process improvement allowing continuous manufacturing routes such as solid oral dosage forms to be implemented (Diab and Gerogiorgis, 2018, 2017; Vanhoorne and Vervaet, 2020) .  \nFeeding is commonly the first step in many pharmaceutical production lines. Although there are different types of feeders, the Loss-in-Weight (LIW) feeder is commonly the most used method to introduce pharmaceutical powders into the process independently of the route of manufacturing due to their ability to control feedrate (Engisch and Muzzio, 2015) . This is key, as the success of a manufacturing route of a solid oral dosage form highly depends on the accuracy and consistency performance of the feeders (Erdemir et al., 2023); a lack of consistent feeding can lead to failure in the quality of the tablet due to content uniformity variation (Blackshields and Crean, 2018; Simonaho et al., 2016) (Blackshields and Crean, 2018; Simonaho et al., 2016) or directly getting the units downstream out of specifications (Engisch and Muzzio, 2012) .  \nLIW feeders consist of a hopper with or without a refill system mounted on top ofa weighing platform. This device measures the material dispensed by the","cbCaiuM5HScxAkEk","https://ap.wps.com/l/cbCaiuM5HScxAkEk","pdf",2471996,57,"English","# Abstract\n# Introduction\n## Continuous manufacturing and digitalised process frameworks\n## Importance of feeding in pharmaceutical production\n## Loss-in-Weight feeder principles\n## Modelling approaches and role of variability","[{\"question\":\"What problem does the document address for Loss-in-Weight feeders?\",\"answer\":\"It addresses predicting feeder mass flow performance parameters under varying material and equipment properties, enabling transferable modelling across different materials and feeder-screw combinations.\"},{\"question\":\"How many machine learning models are used, and what does each do?\",\"answer\":\"Three ML models are used: one predicts feed factor magnitude, another predicts the decay behaviour range, and a final model refines the decay range to a scalar value.\"},{\"question\":\"How does the approach help in pharmaceutical manufacturing planning?\",\"answer\":\"It can be used for equipment pre-selection to determine which feeder-screw combination is likely to deliver the required mass flow.\"}]","A Machine Learning approach to transferable Loss-in-Weight feeder mass flow prediction - abstract | PDF",144]