{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T17:45:55Z","timestamp":1780335955407,"version":"3.54.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T00:00:00Z","timestamp":1618531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T00:00:00Z","timestamp":1618531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100013213","name":"Research Fund for Coal and Steel","doi-asserted-by":"publisher","award":["RFSR-CT-2015-00029"],"award-info":[{"award-number":["RFSR-CT-2015-00029"]}],"id":[{"id":"10.13039\/501100013213","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007176","name":"Scuola Superiore Sant'Anna","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007176","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2022,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This article presents the application of a recent neural network topology known as the deep echo state network to the prediction and modeling of strongly nonlinear systems typical of the process industry. The article analyzes the results by introducing a comparison with one of the most common and efficient topologies, the long short-term memories, in order to highlight the strengths and weaknesses of a reservoir computing approach compared to one currently considered as a standard of recurrent neural network. As benchmark application, two specific processes common in the integrated steelworks are selected, with the purpose of forecasting the future energy exchanges and transformations. The procedures of training, validation and test are based on data analysis, outlier detection and reconciliation and variable selection starting from real field industrial data. The analysis of results shows the effectiveness of deep echo state networks and their strong forecasting capabilities with respect to standard recurrent methodologies both in terms of training procedures and accuracy.<\/jats:p>","DOI":"10.1007\/s00521-021-05984-x","type":"journal-article","created":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T18:03:12Z","timestamp":1618596192000},"page":"911-923","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["A Deep Learning-based approach for forecasting off-gas production and consumption in the blast furnace"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4336-0770","authenticated-orcid":false,"given":"Stefano","family":"Dettori","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9633-5491","authenticated-orcid":false,"given":"Ismael","family":"Matino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9574-0575","authenticated-orcid":false,"given":"Valentina","family":"Colla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramon","family":"Speets","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,4,16]]},"reference":[{"key":"5984_CR1","doi-asserted-by":"publisher","DOI":"10.3386\/w24001","author":"E Brynjolfsson","year":"2017","unstructured":"Brynjolfsson E, Rock D, Syverson C (2017) Artificial intelligence and the modern productivity paradox: A clash of expectations and statistics. National Bureau of Economic Research. https:\/\/doi.org\/10.3386\/w24001","journal-title":"National Bureau of Economic Research"},{"key":"5984_CR2","unstructured":"Ransbotham S, Kiron D, Gerbert P, Reeves M (2017) Reshaping business with artificial intelligence: Closing the gap between ambition and action. MIT Sloan Management Review. 59(1)"},{"issue":"2","key":"5984_CR3","doi-asserted-by":"publisher","first-page":"288","DOI":"10.3390\/met10020288","volume":"10","author":"TA Branca","year":"2020","unstructured":"Branca TA, Fornai B, Colla V, Murri MM, Streppa E, Schr\u00f6der AJ (2020) The Challenge of Digitalization in the Steel Sector. Metals 10(2):288. https:\/\/doi.org\/10.3390\/met10020288","journal-title":"Metals"},{"issue":"6","key":"5984_CR4","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.1109\/72.548162","volume":"7","author":"T Lin","year":"1996","unstructured":"Lin T, Horne BG, Tino P, Giles CL (1996) Learning long-term dependencies in NARX recurrent neural networks. IEEE Trans Neural Networks 7(6):1329\u20131338","journal-title":"IEEE Trans Neural Networks"},{"issue":"4","key":"5984_CR5","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1109\/78.127966","volume":"40","author":"Y Iiguni","year":"1992","unstructured":"Iiguni Y, Sakai H, Tokumaru H (1992) A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter. IEEE Transactions on Signal processing. 40(4):959\u2013966","journal-title":"IEEE Transactions on Signal processing"},{"issue":"2","key":"5984_CR6","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks. 5(2):157\u2013166","journal-title":"IEEE Transactions on Neural Networks."},{"key":"5984_CR7","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y (2013) On the difficulty of training recurrent neural networks. In International conference on machine learning. 1310\u20131318."},{"issue":"8","key":"5984_CR8","doi-asserted-by":"publisher","first-page":"1889","DOI":"10.1162\/089976600300015187","volume":"12","author":"Yoshua Bengio","year":"2000","unstructured":"Bengio Yoshua (2000) Gradient-based optimization of hyperparameters. Neural Computation. 12(8):1889\u20131900","journal-title":"Neural Computation."},{"issue":"11","key":"5984_CR9","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1162\/089976602760407955","volume":"14","author":"W Maass","year":"2002","unstructured":"Maass W, Natschl\u00e4ger T, Markram H (2002) Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation. 14(11):2531\u20132560","journal-title":"Neural Computation."},{"key":"5984_CR10","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1016\/j.energy.2018.04.175","volume":"155","author":"L Wang","year":"2018","unstructured":"Wang L, Lv S-X, Zeng Y-R (2018) Effective sparse adaboost method with ESN and FOA for industrial electricity consumption forecasting in China. Energy 155:1013\u20131031. https:\/\/doi.org\/10.1016\/j.energy.2018.04.175","journal-title":"Energy"},{"key":"5984_CR11","doi-asserted-by":"publisher","first-page":"1931","DOI":"10.1109\/ACCESS.2015.2485943","volume":"3","author":"FM Bianchi","year":"2015","unstructured":"Bianchi FM, De Santis E, Rizzi A, Sadeghian A (2015) Short-Term Electric Load Forecasting Using Echo State Networks and PCA Decomposition. IEEE Access 3:1931\u20131943","journal-title":"IEEE Access"},{"key":"5984_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05113-0","author":"H Zhang","year":"2020","unstructured":"Zhang H, Yang Y, Zhang Y et al (2020) A combined model based on SSA, neural networks and LSSVM for short-term electric load and price forecasting. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-020-05113-0","journal-title":"Neural Comput Appl"},{"key":"5984_CR13","doi-asserted-by":"publisher","first-page":"113578","DOI":"10.1016\/j.apenergy.2019.113578","volume":"253","author":"I Matino","year":"2019","unstructured":"Matino I, Dettori S, Colla V, Weber V, Salame S (2019) Forecasting blast furnace gas production and demand through echo state neural network-based models: Pave the way to off-gas optimized management. Appl Energy 253:113578. https:\/\/doi.org\/10.1016\/j.apenergy.2019.113578","journal-title":"Appl Energy"},{"key":"5984_CR14","doi-asserted-by":"publisher","first-page":"4061","DOI":"10.1016\/j.egypro.2019.01.831","volume":"158","author":"S Dettori","year":"2019","unstructured":"Dettori S, Matino I, Colla V, Weber V, Salame S (2019) Neural network-based modeling methodologies for energy transformation equipment in integrated steelworks processes. Energy Procedia 158:4061\u20134066. https:\/\/doi.org\/10.1016\/j.egypro.2019.01.831","journal-title":"Energy Procedia"},{"key":"5984_CR15","doi-asserted-by":"publisher","unstructured":"Colla, V., Matino, I., Dettori, S., Cateni, S., Matino, R (2019) Reservoir Computing Approaches Applied to Energy Management in Industry. International Conference on Engineering Applications of Neural Networks, pp.66\u201379, Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-20257-6_6.","DOI":"10.1007\/978-3-030-20257-6_6"},{"issue":"8","key":"5984_CR16","doi-asserted-by":"publisher","first-page":"3089","DOI":"10.1109\/tie.2011.2169636","volume":"59","author":"Y Pan","year":"2011","unstructured":"Pan Y, Wang J (2011) Model predictive control of unknown nonlinear dynamical systems based on recurrent neural networks. IEEE Trans Industr Electron 59(8):3089\u20133101. https:\/\/doi.org\/10.1109\/tie.2011.2169636","journal-title":"IEEE Trans Industr Electron"},{"key":"5984_CR17","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.neucom.2016.12.089","volume":"268","author":"C Gallicchio","year":"2017","unstructured":"Gallicchio C, Micheli A, Pedrelli L (2017) Deep reservoir computing: a critical experimental analysis. Neurocomputing 268:87\u201399. https:\/\/doi.org\/10.1016\/j.neucom.2016.12.089","journal-title":"Neurocomputing"},{"issue":"23","key":"5984_CR18","doi-asserted-by":"publisher","first-page":"17769","DOI":"10.1007\/s00521-020-04948-x","volume":"32","author":"T Kim","year":"2020","unstructured":"Kim T, King BR (2020) Time series prediction using deep echo state networks. Neural Comput Appl 32(23):17769\u201317787","journal-title":"Neural Comput Appl"},{"key":"5984_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05286-8","author":"R Hu","year":"2020","unstructured":"Hu R, Tang ZR, Song X et al (2020) Ensemble echo network with deep architecture for time-series modeling. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-020-05286-8","journal-title":"Neural Comput Appl"},{"key":"5984_CR20","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1016\/j.neunet.2018.08.025","volume":"108","author":"L Grigoryeva","year":"2018","unstructured":"Grigoryeva L, Ortega JP (2018) Echo state network are universal. Neural Netw 108:495\u2013508. https:\/\/doi.org\/10.1016\/j.neunet.2018.08.025","journal-title":"Neural Netw"},{"issue":"3","key":"5984_CR21","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/s12559-017-9461-9","volume":"9","author":"C Gallicchio","year":"2017","unstructured":"Gallicchio C, Micheli A (2017) Echo state property of deep reservoir computing networks. Cogn Comput 9(3):337\u2013350. https:\/\/doi.org\/10.1007\/s12559-017-9461-9","journal-title":"Cogn Comput"},{"key":"5984_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2012.07.005","volume":"35","author":"IB Yildiz","year":"2012","unstructured":"Yildiz IB, Jaeger H, Kiebel SJ (2012) Re-visiting the echo state property. Neural Netw 35:1\u20139. https:\/\/doi.org\/10.1016\/j.neunet.2012.07.005","journal-title":"Neural Netw"},{"issue":"8","key":"5984_CR23","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"5984_CR24","unstructured":"Janjua, R., Energy use in steel industry, World Steel Association, http:\/\/www.iipinetwork.org, last accessed 2020\/10\/15."},{"key":"5984_CR25","doi-asserted-by":"publisher","first-page":"2156","DOI":"10.1016\/j.apenergy.2009.11.031","volume":"87","author":"H Kong","year":"2010","unstructured":"Kong H, Qi E, Li H, Gang L, Xing Z (2010) An MILP model for optimisation of byproduct gases in the integrated iron and steel plant. Appl Energy 87:2156\u20132163","journal-title":"Appl Energy"},{"issue":"2","key":"5984_CR26","doi-asserted-by":"publisher","first-page":"1148","DOI":"10.1016\/j.applthermaleng.2014.05.058","volume":"70","author":"GF Porzio","year":"2014","unstructured":"Porzio GF, Colla V, Matarese N, Nastasi G, Branca TA, Amato A, Fornai B, Vannucci M, Bergamasco M (2014) Process integration in energy and carbon intensive industries: An example of exploitation of optimization techniques and decision support. Appl Therm Eng 70(2):1148\u20131155. https:\/\/doi.org\/10.1016\/j.applthermaleng.2014.05.058","journal-title":"Appl Therm Eng"},{"key":"5984_CR27","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1016\/j.applthermaleng.2015.08.051","volume":"91","author":"A Maddaloni","year":"2015","unstructured":"Maddaloni A, Porzio GF, Nastasi G, Colla V, Branca TA (2015) Multi-objective optimization applied to retrofit analysis: A case study for the iron and steel industry. Appl Therm Eng 91:638\u2013646. https:\/\/doi.org\/10.1016\/j.applthermaleng.2015.08.051","journal-title":"Appl Therm Eng"},{"key":"5984_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Gu, Y. L., Ti, W., Cai, J. J (2012) Supply and demand forecasting of blast furnace gas based on artificial neural network in iron and steel works, Advanced Materials Research. 443; 183\u2013188. Trans Tech Publications.","DOI":"10.4028\/www.scientific.net\/AMR.443-444.183"},{"key":"5984_CR29","doi-asserted-by":"crossref","unstructured":"Yang, L., He, K., Zhao, X., Lv, Z. The prediction for output of blast furnace gas based on genetic algorithm and LSSVM, Proc. 9th IEEE Conference on Industrial Electronics and Applications (ICIEA), 1493\u20131498, (2014).","DOI":"10.1109\/ICIEA.2014.6931405"},{"key":"5984_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, X., He, K., Yang, L (2014) The model of prediction of Blast Furnace Gas Output. Proc. 9th IEEE Conference on Industrial Electronics and Applications (ICIEA). 1489\u20131492.","DOI":"10.1109\/ICIEA.2014.6931404"},{"issue":"4","key":"5984_CR31","doi-asserted-by":"publisher","first-page":"889","DOI":"10.3233\/ifs-2012-0607","volume":"24","author":"S Cateni","year":"2013","unstructured":"Cateni S, Colla V, Nastasi G (2013) A multivariate fuzzy system applied for outliers detection. Journal of Intelligent and Fuzzy Systems 24(4):889\u2013903. https:\/\/doi.org\/10.3233\/ifs-2012-0607","journal-title":"Journal of Intelligent and Fuzzy Systems"},{"key":"5984_CR32","first-page":"561","volume":"2007","author":"S Cateni","year":"2007","unstructured":"Cateni S, Colla V, Vannucci M (2007) A fuzzy logic-based method for outliers detection. Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007:561\u2013566","journal-title":"Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA"},{"key":"5984_CR33","doi-asserted-by":"publisher","unstructured":"Cateni, S., Colla, V., Vannucci, M (2009) General purpose input variables extraction: A genetic algorithm based procedure GIVE a GAP. 9th International Conference on Intelligent Systems Design and Applications ISDA. 2009, pp. 1278\u20131283. https:\/\/doi.org\/10.1109\/isda.2009.190.","DOI":"10.1109\/isda.2009.190"},{"issue":"2","key":"5984_CR34","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/ems.2010.23","volume":"12","author":"S Cateni","year":"2011","unstructured":"Cateni S, Colla V, Vannucci M (2011) A genetic algorithm-based approach for selecting input variables and setting relevant network parameters of a SOM-based classifier. Int J Simul Syst Sci Technol 12(2):30\u201337. https:\/\/doi.org\/10.1109\/ems.2010.23","journal-title":"Int J Simul Syst Sci Technol"},{"key":"5984_CR35","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.neunet.2018.08.002","volume":"108","author":"C Gallicchio","year":"2018","unstructured":"Gallicchio C, Micheli A, Pedrelli L (2018) Design of deep echo state networks. Neural Netw 108:33\u201347. https:\/\/doi.org\/10.1016\/j.neunet.2018.08.002","journal-title":"Neural Netw"},{"key":"5984_CR36","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:281\u2013305","journal-title":"J Mach Learn Res"},{"key":"5984_CR37","unstructured":"Kingma, Diederik P., Jimmy Ba (2014) \"Adam: A method for stochastic optimization.\" arXiv preprint."}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05984-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-05984-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05984-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T15:22:56Z","timestamp":1642778576000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-05984-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,16]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["5984"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-05984-x","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,16]]},"assertion":[{"value":"5 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interests regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}