{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T03:59:42Z","timestamp":1777694382417,"version":"3.51.4"},"reference-count":33,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Integrated Computer-Aided Engineering"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:p>Industrial processes are becoming increasingly complex, requiring advanced modelling techniques to understand their behaviour and improve their performance. In this context, deep learning algorithms have proven to be effective tools for modelling dynamic systems, with Recurrent Neural Networks (RNNs) being particularly suitable for time-series data. However, the computational complexity of deep learning models can be a limitation in industrial environments, where real-time responses are required.<\/jats:p>\n                  <jats:p>\n                    \n                    This work proposes the use of Deep Echo State Networks to model an industrial system. The aim is to evaluate its performance in real-time industrial applications when running on embedded devices. The approach is validated on a process composed of four interconnected water tanks, which exhibits typical nonlinear industrial\u00a0dynamics. Among several candidate architectures (including vanilla RNNs or LSTMs), Deep ESNs were selected for their balance of accuracy and computational efficiency. Different input-output\u00a0setups and number of Deep ESN layers are tested, and results are compared with LSTMs in terms of accuracy and execution time. Finally, the best Deep ESN models are implemented on industrial embedded devices to evaluate the possibility of running these models in real time.\n                  <\/jats:p>\n                  <jats:p>\n                    \n                    The proposed approach achieved up to a 33% reduction in RMSE and a 14% improvement in\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" overflow=\"scroll\">\n                        <mml:msup>\n                          <mml:mi>R<\/mml:mi>\n                          <mml:mn>2<\/mml:mn>\n                        <\/mml:msup>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    compared to traditional reservoir computing, highlighting its superior predictive performance. The results show that Deep ESN models can effectively model the industrial system, with the best configurations achieving high accuracy and low execution times, demonstrating the feasibility of running these models in real time in industrial environments.\n                  <\/jats:p>","DOI":"10.1177\/10692509251376129","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:35:12Z","timestamp":1760711712000},"page":"55-71","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Embedded deep reservoir computing for modelling complex industrial systems"],"prefix":"10.1177","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0401-3995","authenticated-orcid":false,"given":"Jos\u00e9","family":"Ram\u00f3n Rodr\u00edguez-Ossorio","sequence":"first","affiliation":[{"name":"SUPPRESS research group, University of Le\u00f3n, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6692-2564","authenticated-orcid":false,"given":"Claudio","family":"Gallicchio","sequence":"additional","affiliation":[{"name":"University of Pisa"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2762-6949","authenticated-orcid":false,"given":"Antonio","family":"Mor\u00e1n","sequence":"additional","affiliation":[{"name":"SUPPRESS research group, University of Le\u00f3n, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0420-2315","authenticated-orcid":false,"given":"Ignacio","family":"D\u00edaz","sequence":"additional","affiliation":[{"name":"University of Oviedo"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9023-0341","authenticated-orcid":false,"given":"Juan J","family":"Fuertes","sequence":"additional","affiliation":[{"name":"SUPPRESS research group, University of Le\u00f3n, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3921-1599","authenticated-orcid":false,"given":"Manuel","family":"Dom\u00ednguez","sequence":"additional","affiliation":[{"name":"SUPPRESS research group, University of Le\u00f3n, Spain"}]}],"member":"179","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-230711"},{"key":"e_1_3_2_3_2","first-page":"89","article-title":"State of the art in structural health monitoring of offshore and marine structures","volume":"176","author":"Pezeshki H","year":"2023","unstructured":"Pezeshki H, Adeli H, Pavlou D, et\u00a0al. State of the art in structural health monitoring of offshore and marine structures. Proc Inst Civil Eng - Maritime Eng 2023; 176: 89\u2013108.","journal-title":"Proc Inst Civil Eng - Maritime Eng"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3136357"},{"key":"e_1_3_2_5_2","unstructured":"Salehinejad H Sankar S Barfett J et\u00a0al. Recent Advances in Recurrent Neural Networks 2018. 10.48550\/arXiv.1801.01078. ArXiv:1801.01078 [cs]."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-240734"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-230727"},{"key":"e_1_3_2_9_2","first-page":"45","article-title":"An efficient deep learning model for real-time fault diagnosis in industrial systems","volume":"32","author":"Smith J","year":"2024","unstructured":"Smith J, Kumar A, Zhang L. An efficient deep learning model for real-time fault diagnosis in industrial systems. Integr Comput Aided Eng 2024; 32: 45\u201360.","journal-title":"Integr Comput Aided Eng"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-240740"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-230719"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-240738"},{"key":"e_1_3_2_13_2","unstructured":"Gao W Hu Q Ye Z et\u00a0al. Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy Challenges and Vision 2022. 10.48550\/arXiv.2205.11913. ArXiv:2205.11913 [cs]."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00463-x"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Tortorella D Gallicchio C Micheli A. Hierarchical dynamics in deep echo state networks. In: Pimenidis E Angelov P Jayne C et\u00a0al. (eds.) Artificial neural networks and machine learning \u2013 ICANN 2022. Lecture Notes in Computer Science 2022 pp.668\u2013679. Cham: Springer Nature Switzerland. ISBN 978-3-031-15934-3. DOI: 10.1007\/978-3-031-15934-3_55.","DOI":"10.1007\/978-3-031-15934-3_55"},{"key":"e_1_3_2_17_2","first-page":"215","article-title":"Adaptive reservoir computing for time-series prediction in manufacturing processes","volume":"30","author":"Lee M","year":"2022","unstructured":"Lee M, Tanaka S, Gupta R. Adaptive reservoir computing for time-series prediction in manufacturing processes. Integr Comput Aided Eng 2022; 30: 215\u2013230.","journal-title":"Integr Comput Aided Eng"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2009.03.005"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.089"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Gallicchio C Micheli A Pedrelli L. Hierarchical temporal representation in linear reservoir computing. In: Esposito A Faundez-Zanuy M Morabito FC et\u00a0al. (eds.) Neural advances in processing nonlinear dynamic signals. Smart Innovation Systems and Technologies 2019 pp.119\u2013129. Cham: Springer International Publishing. ISBN 978-3-319-95098-3. DOI: 10.1007\/978-3-319-95098-3_11.","DOI":"10.1007\/978-3-319-95098-3_11"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3225780"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez-Ossorio JR Gallicchio C Mor\u00e1n A et\u00a0al. Deep echo state networks for modelling of industrial systems. In: Engineering applications of neural networks 2024 pp.106\u2013119. Cham: Springer Nature Switzerland. ISBN 978-3-031-62495-7. DOI: 10.1007\/978-3-031-62495-7_9.","DOI":"10.1007\/978-3-031-62495-7_9"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2022.100300"},{"key":"e_1_3_2_24_2","first-page":"13","article-title":"The \u201cecho state\u201d approach to analysing and training recurrent neural networks-with an erratum note","volume":"148","author":"Jaeger H","year":"2001","unstructured":"Jaeger H. The \u201cecho state\u201d approach to analysing and training recurrent neural networks-with an erratum note. Bonn, Germany: German Natl Res Cent Inform Technol GMD Techn Rep 2001; 148: 13.","journal-title":"Bonn, Germany: German Natl Res Cent Inform Technol GMD Techn Rep"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2007.04.016"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2011.02.002"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.07.005"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Luko\u0161evi\u010dius M. A practical guide to applying echo state networks. In: Neural Networks: Tricks of the Trade: Second Edition 2012. pp.659\u2013686. Berlin Heidelberg: Springer Berlin Heidelberg. ISBN 978-3-642-35289-8. DOI: 10.1007\/978-3-642-35289-8_36.","DOI":"10.1007\/978-3-642-35289-8_36"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-017-9461-9"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.08.002"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Trouvain N Pedrelli L Dinh TT et\u00a0al. Reservoirpy: An efficient and user-friendly library to design echo state networks. In: Artificial neural networks and machine learning \u2013 ICANN 2020 2020 pp.494\u2013505. Cham: Springer International Publishing. ISBN 978-3-030-61616-8. DOI: 10.1007\/978-3-030-61616-8_40.","DOI":"10.1007\/978-3-030-61616-8_40"},{"key":"e_1_3_2_32_2","unstructured":"Abadi M et\u00a0al. TensorFlow: Large-scale machine learning on heterogeneous systems 2015. https:\/\/www.tensorflow.org\/. Software available from tensorflow.org."},{"key":"e_1_3_2_33_2","unstructured":"Chollet F et\u00a0al. Keras. https:\/\/keras.io 2015."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/87.845876"}],"container-title":["Integrated Computer-Aided Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10692509251376129","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/10692509251376129","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10692509251376129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:15:02Z","timestamp":1777454102000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/10692509251376129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1177\/10692509251376129"],"URL":"https:\/\/doi.org\/10.1177\/10692509251376129","relation":{},"ISSN":["1069-2509","1875-8835"],"issn-type":[{"value":"1069-2509","type":"print"},{"value":"1875-8835","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]}}}