{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T05:24:23Z","timestamp":1786944263936,"version":"build-2736575974"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>\n                    Blast furnace (BF) operation involves strongly coupled thermal and chemical processes governed by nonlinear heat transfer, gas\u2013solid reactions, and dynamic operational control. Accurate real-time prediction of key thermal and gas parameters is essential for maintaining furnace stability, improving energy efficiency, and reducing carbon emissions. However, most existing studies focus on single-parameter forecasting and fail to adequately capture the heterogeneous temporal dynamics and strong process coupling inherent in blast furnace operations. In this paper, a hybrid fuzzy clustering and temporal deep learning framework is proposed for multi-parameter forecasting. This framework integrates Fuzzy C-Means (FCM) clustering with temporal deep learning models, such as Nonlinear Autoregressive with Exogenous Inputs (NARX), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The dataset consists of 43,396 industrial Distributed Control System (DCS) samples collected from an operating BF. FCM is employed to identify different operating regimes and generate fuzzy membership values, which are subsequently utilized as sample weights during model training. The performance of the proposed models is evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and coefficient of determination (\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    ). Among the developed models, the FCM-GRU model achieved the best overall forecasting performance, attaining\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    values of 0.602, 0.355, 0.656, and 0.912 for the prediction of Hot Metal Temperature (HMT), silicon content (Si), CO, and CO\u2082 respectively. The novelty of the proposed work lies in integrating fuzzy membership-based operational-state identification with temporal deep learning architectures for simultaneous forecasting of multiple blast furnace parameters. The obtained results demonstrate the feasibility of the proposed framework for real-time process monitoring and predictive decision support in blast furnace operations.\n                  <\/jats:p>","DOI":"10.3389\/frai.2026.1826705","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T04:31:40Z","timestamp":1786941100000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid fuzzy clustering and temporal deep learning framework for multi-parameter forecasting in industrial thermal processes"],"prefix":"10.3389","volume":"9","author":[{"given":"V.","family":"Vignesh","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Vellore Institute of Technology","place":["Chennai, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G. V.","family":"Narendran","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Vellore Institute of Technology","place":["Chennai, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Senthil Kumar","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Vellore Institute of Technology","place":["Chennai, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Sitharthan","sequence":"additional","affiliation":[{"name":"Centre for Smart Grid Technologies, Vellore Institute of Technology","place":["Chennai, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"4134","DOI":"10.3390\/su17094134","article-title":"Sustain AI: a multi-modal deep learning framework for carbon footprint reduction in industrial manufacturing","volume":"17","author":"Alghieth","year":"2025","journal-title":"Sustainability"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"109868","DOI":"10.1016\/j.rineng.2026.109868","article-title":"Optimizing smart grid performance: a GRU approach to electric power forecasting and demand side management","volume":"29","author":"Balakumar","year":"2026","journal-title":"Results Eng."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"108955","DOI":"10.1016\/j.engappai.2024.108955","article-title":"Fuzzy C-Means clustering based selective edge enhancement scheme for improved road crack detection","volume":"136","author":"Bhardwaj","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref4","volume-title":"That\u2019s about What every Hour a Blast Furnace\u2019s Downtime May Cost to a Company","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"4045","DOI":"10.1007\/s00170-024-13214-6","article-title":"Deep learning for robust forecasting of hot metal silicon content in a blast furnace","volume":"136","author":"Giannetti","year":"2025","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref6","volume-title":"Unplanned Downtime: A Multi-Million Dollar Drain in Steel Manufacturing","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2025.3566715","article-title":"Multivariable prediction of blast furnace status driven by data","volume":"74","author":"Guo","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref8","author":"Hamidi","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.3390\/math13081347","article-title":"A multi-scale fusion convolutional network for time-series silicon prediction in blast furnaces","volume":"13","author":"Hao","year":"2025","journal-title":"Mathematics"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"129712","DOI":"10.1016\/j.neucom.2025.129712","article-title":"LSTM and GRU type recurrent neural networks in model predictive control: a review","volume":"632","author":"\u0141awry\u0144czuk","year":"2025","journal-title":"Neurocomputing"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"11369","DOI":"10.1109\/tnnls.2024.3453280","article-title":"Denoising multiscale spectral graph wavelet neural networks for gas utilization ratio prediction in blast furnace","volume":"36","author":"Liu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"125819","DOI":"10.1016\/j.apenergy.2025.125819","article-title":"Knowledge-and data-driven prediction of blast furnace gas generation and consumption in iron and steel sites","volume":"390","author":"Liu","year":"2025","journal-title":"Appl. Energy"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"2607","DOI":"10.3390\/polym16182607","article-title":"Applications of long short-term memory (LSTM) networks in polymeric sciences: a review","volume":"16","author":"Malashin","year":"2024","journal-title":"Polymers"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.2355\/isijinternational.isijint-2024-028","article-title":"Prediction of silicon content of hot metal in blast furnace based on Optuna-GBDT","volume":"64","author":"Meng","year":"2024","journal-title":"ISIJ Int."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"091009","DOI":"10.1115\/1.4068835","article-title":"Experimental validation of convolutional neural network-based fault detection in power overhead lines using integrated thermal imaging and current measurement techniques","volume":"17","author":"Meradi","year":"2025","journal-title":"J. Therm. Sci. Eng. Appl."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"109210","DOI":"10.1016\/j.compchemeng.2025.109210","article-title":"A machine learning approach for intra- and inter-cast hot metal temperature forecasting","volume":"201","author":"Paix\u00e3o","year":"2025","journal-title":"Comput. Chem. Eng."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"34694","DOI":"10.1109\/jiot.2024.3416733","article-title":"Machine and deep learning for digital twin networks: a survey","volume":"11","author":"Qin","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"108871","DOI":"10.1016\/j.icheatmasstransfer.2025.108871","article-title":"A novel hybrid deep learning algorithm for estimating temperature-dependent thermal conductivity in transient heat conduction problems","volume":"164","author":"Qiu","year":"2025","journal-title":"Int. Commun. Heat Mass Transfer"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"632","DOI":"10.3390\/ma18030632","article-title":"Prediction of silicon content in a blast furnace via machine learning: a comprehensive processing and modeling pipeline","volume":"18","author":"Raza","year":"2025","journal-title":"Materials (Basel, Switzerland)"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s10792-024-03157-y","article-title":"Chasing the objective upper eyelid symmetry formula; R2, RMSE, POC, MAE, and MSE","volume":"44","author":"Serefoglu Cabuk","year":"2024","journal-title":"Int. Ophthalmol."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1007\/s12613-023-2693-7","article-title":"Process metallurgy and data-driven prediction and feedback of blast furnace heat indicators","volume":"31","author":"Shi","year":"2024","journal-title":"Int. J. Miner. Metall. Mater."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"407","DOI":"10.2298\/jmmb240928033s","article-title":"Prediction model of blast furnace molten iron temperature and molten iron silicon content based on improved arithmetic optimization twin support vector machine for regression","volume":"60","author":"Shi","year":"2024","journal-title":"J. Min. Metall. B Metall."},{"key":"ref23","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"139882","DOI":"10.1016\/j.energy.2025.139882","article-title":"Hybrid deep learning framework for high-precision prediction of transient thermal-flow in supercritical LNG heat exchangers","volume":"344","author":"Sun","year":"2026","journal-title":"Energy"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"6143","DOI":"10.21105\/joss.06143","article-title":"Permetrics: a framework of performance metrics for machine learning models","volume":"9","author":"Thieu","year":"2024","journal-title":"J. Open Source Softw."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"102946","DOI":"10.1016\/j.mex.2024.102946","article-title":"A critical review of RNN and LSTM variants in hydrological time series predictions","volume":"13","author":"Waqas","year":"2024","journal-title":"MethodsX"},{"key":"ref27","year":"2024"},{"key":"ref28","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2024.3458070","article-title":"Soft sensor for blast furnace temperature field based on digital twin","volume":"73","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2025.3565252","article-title":"Prediction of carbon emission concentrations in blast furnaces based on digital twin","volume":"74","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"132273","DOI":"10.1016\/j.fuel.2024.132273","article-title":"A machine learning and CFD modeling hybrid approach for predicting real-time heat transfer during cokemaking processes","volume":"373","author":"Zhao","year":"2024","journal-title":"Fuel"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1826705\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T04:31:47Z","timestamp":1786941107000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1826705\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":31,"alternative-id":["10.3389\/frai.2026.1826705"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1826705","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]},"article-number":"1826705"}}