[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-355360-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-355360-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","temporal-fusion-enhanced-network-for-early-prediction-of-ethanol-fermentation-performance-using-initial-tank-information","Temporal Fusion Enhanced Network for Early Prediction of Ethanol Fermentation Performance Using Initial Tank Information","","Accurate prediction of out-of-tank ethanol concentration is essential for controlling and optimizing industrial fuel ethanol fermentation. The process is a long-period batch operation whose performance is influenced by static initial tank entry variables and dynamic time-series and compositional variables, typically requiring 0–40 h sampling that delays timely prediction. This study proposes TFEN, which extracts temporally fused features, reconstructs relationships to static variables, and predicts performance using only initial static information. Experiments show improved accuracy versus baselines, with best normalized RMSE of 0.0526 (0.339 g/100 mL).",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/temporal-fusion-enhanced-network-for-early-prediction-of-ethanol-fermentation-performance-using-initial-tank-information/355360/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/temporal-fusion-enhanced-network-for-early-prediction-of-ethanol-fermentation-performance-using-initial-tank-information/355360.png","ImageObject",300,407,{"name":42,"@type":43},"Anna Hans","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-14","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is early prediction of out-of-tank ethanol concentration important?","Question",{"text":63,"@type":64},"It directly supports process control and optimization by enabling timely decisions based on an essential performance indicator of ethanol fermentation.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What input limitation motivates the proposed TFEN approach?",{"text":68,"@type":64},"Dynamic variables generally require sampling over 0–40 hours, which creates delays and prevents timely prediction using conventional time-dependent inputs.",{"name":70,"@type":61,"acceptedAnswer":71},"How does TFEN enable prediction using only initial tank information?",{"text":72,"@type":64},"TFEN fuses temporally learned features from historical data, reconstructs hidden relationships to static variables, and then uses reconstructed static-driven features to train a model that predicts fermentation performance from the beginning-of-production information.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},355360,1790814267,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},5909892332657,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","International Journal of Control, Automation, and Systems (2026) 24:1855–1869  \n[https://doi.org/10.1007/s12555-026-00106-6](https://doi.org/10.1007/s12555-026-00106-6)  \nTemporal Fusion Enhanced Network for Early Prediction of Ethanol Fermentation Performance Using Initial Tank Information  \nYichao Xia1 · Yifei Sun1 · Yufeng Dong1 · Xuefeng Yan1  \nReceived: 20 January 2025 / Revised: 1 March 2026 / Accepted: 14 April 2026 / Published online: 19 May 2026  \n© The Author(s), under exclusive licence to Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers 2026  \nAbstract  \nIn the industrial fuel ethanol fermentation process, accurate prediction of out-of-tank ethanol concentration, i.e., its main performance, is essential for its control and optimization. However, ethanol fermentation is a long-period batch process, whose performance is affected by multiple static variables, i.e., initial tank entry information, and dynamic variables, including time-series operational variables and compositional variables sampled at different time points. Existing prediction models are usually based on static variables and dynamic variables. However, dynamic variables generally require sampling over a period of 0–40 h, resulting in delays in the timely prediction of fermentation performance. To address this challenge, this paper proposes a novel model called the Temporal Fusion Enhanced Network (TFEN) . First, the enhancement module extracts temporally fused features from historical data, including static variables atthe beginning ofproduction, low-frequency dynamic variables sampled at different hours, and high-frequency dynamic variables. Second, the reconstruction module learns the hidden relationship between temporally fused features and static variables. Third, static variables from the dataset are passed through the reconstruction module to generate new features, which are used to train the model. Finally, TFEN can accurately predict the ethanol fermentation performance only based on static variables at the beginning of production. Comparative experiments indicate that the predictive performance of TFEN not only surpasses that of other algorithms, but also exceeds the results of the model employing static variables and dynamic variables at 8 h and 24 h as the input variables. Moreover, its accuracy is close to the model with other dynamic variables at 40 h. Also, the more comprehensive the historical data is, the more accurate TFEN is. The proposed TFEN achieves the best prediction accuracy with an RMSE of 0.0526 (normalized), corresponding to 0.339 g/100 mL in physical units.  \nKeywords Temporal fusion enhanced network · Batch process · Fuel ethanol fermentation · Static variables · Dynamic variables  \nRecommended by Associate Editor Seongmin Heo under the direction of Senior Editor Jong Min Lee.  \nB Xuefeng Yan[xfyan@ecust.edu.cn](xfyan@ecust.edu.cn)  \nYichao Xia  \n[y30230968@mail.ecust.edu.cn](y30230968@mail.ecust.edu.cn)  \nYifei Sun  \n[y21220030@mail.ecust.edu.cn](y21220030@mail.ecust.edu.cn)  \nYufeng Dong  \n[y20190056@mail.ecust.edu.cn](y20190056@mail.ecust.edu.cn)  \n1 Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education East, China University of Science and Technology, MeiLong Road NO. 130, P.O. BOX  \n293, Shanghai 200237, People’s Republic of China  \n1 Introduction  \nThe inevitable decrease in nonrenewable energy sources has necessitated the use of renewable energy sources. Bioenergy has drawn much attention due to low environmental impact and production cost [1] . Fuel ethanol, a bioenergy source, is increasingly used worldwide. As a key indicator of the ethanol fermentation process, early prediction of out-of-tank ethanol concentration is essential for optimizing the process. The out-of-tank ethanol concentration is inﬂuenced by both initial tank information and process dynamic information. It takes a long time (usually several hours or more) to acquire the la","cbCaifnRLh0s4yxj","https://ap.wps.com/l/cbCaifnRLh0s4yxj","pdf",1910760,15,"English","# Abstract\n## Introduction\n## Related Work","[{\"question\":\"Why is early prediction of out-of-tank ethanol concentration important?\",\"answer\":\"It directly supports process control and optimization by enabling timely decisions based on an essential performance indicator of ethanol fermentation.\"},{\"question\":\"What input limitation motivates the proposed TFEN approach?\",\"answer\":\"Dynamic variables generally require sampling over 0–40 hours, which creates delays and prevents timely prediction using conventional time-dependent inputs.\"},{\"question\":\"How does TFEN enable prediction using only initial tank information?\",\"answer\":\"TFEN fuses temporally learned features from historical data, reconstructs hidden relationships to static variables, and then uses reconstructed static-driven features to train a model that predicts fermentation performance from the beginning-of-production information.\"}]","Temporal Fusion Enhanced Network for Early Prediction of Ethanol Fermentation Performance Using Initial Tank Information | PDF",1790118064,38,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e548f6a4b3d071735da988fb2103cde5.webp",983,1305,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/04d4fac92c2c466989b0de435741a1de.webp",982,1304,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6952074f0f26112acf9c315cbf0d77bb.webp",981,1303,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f9b2d90168bdde4781acca7bcec14dd8.webp",980,1301]