{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:09:43Z","timestamp":1766138983758,"version":"3.41.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Measurement of certain variables within the industrial sector remains a challenge due to the prohibitive costs of sensors, the intricate installation processes, or the continuous nature of production demands. Moreover, if a backup sensor is required in case the main sensor fails, the installation and maintenance difficulties are further increased. A possibility to address this issue is the indirect estimation of the desired variable by leveraging other correlated measures within the operational process. Data-driven techniques are well-suited for this aim, given their capacity to model potentially complex industrial processes. This paper proposes the implementation of a virtual flow sensor for its integration in the control loop of an industrial process. More specifically, four different data-driven methods have been tested to obtain the virtual sensor: multiple linear regression (MLR), multilayer perceptron (MLP), long-short term memory (LSTM) and deep long-short term memory (DeepLSTM). MAE, RMSE and <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>$$R^2$$<\/jats:tex-math>\n                <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msup>\n                    <mml:mi>R<\/mml:mi>\n                    <mml:mn>2<\/mml:mn>\n                  <\/mml:msup>\n                <\/mml:math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula> have been chosen as evaluation metrics for model selection and testing. Furthermore, the robustness of the virtual flow sensor is not only evaluated under ideal operating conditions, but it is also tested under adverse conditions with various noise levels added to the measured signals. Additionally, the performance of the flow control loop using the real and virtual sensors is also evaluated in both ideal and adverse conditions. IAE, ITAE, and IAVU indices are used to assess the control performance. The results prove the robustness of the LSTM-based virtual flow sensor and the effectiveness of the control loop using it, avoiding the modification of the controller and interrupting the process when the real flow sensor fails.<\/jats:p>","DOI":"10.1007\/s00521-024-10560-0","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T13:53:09Z","timestamp":1733147589000},"page":"10507-10519","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Assessment and deployment of a LSTM-based virtual sensor in an industrial process control loop"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4544-5786","authenticated-orcid":false,"given":"Ra\u00fal","family":"Gonz\u00e1lez-Herb\u00f3n","sequence":"first","affiliation":[]},{"given":"Guzm\u00e1n","family":"Gonz\u00e1lez-Mateos","sequence":"additional","affiliation":[]},{"given":"Jos\u00e9 R.","family":"Rodr\u00edguez-Ossorio","sequence":"additional","affiliation":[]},{"given":"Miguel A.","family":"Prada","sequence":"additional","affiliation":[]},{"given":"Antonio","family":"Mor\u00e1n","sequence":"additional","affiliation":[]},{"given":"Seraf\u00edn","family":"Alonso","sequence":"additional","affiliation":[]},{"given":"Juan J.","family":"Fuertes","sequence":"additional","affiliation":[]},{"given":"Manuel","family":"Dom\u00ednguez","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"10560_CR1","doi-asserted-by":"publisher","first-page":"2727","DOI":"10.1007\/s00521-017-3225-z","volume":"31","author":"M Abdel-Nasser","year":"2019","unstructured":"Abdel-Nasser M, Mahmoud K (2019) Accurate photovoltaic power forecasting models using deep lstm-rnn. Neural Comput Appl 31:2727\u20132740","journal-title":"Neural Comput Appl"},{"issue":"8","key":"10560_CR2","doi-asserted-by":"publisher","first-page":"2801","DOI":"10.1109\/JSEN.2018.2885609","volume":"19","author":"C Abeykoon","year":"2018","unstructured":"Abeykoon C (2018) Design and applications of soft sensors in polymer processing: a review. IEEE Sens J 19(8):2801\u20132813. https:\/\/doi.org\/10.1109\/JSEN.2018.2885609","journal-title":"IEEE Sens J"},{"issue":"23","key":"10560_CR3","doi-asserted-by":"publisher","first-page":"17291","DOI":"10.1007\/s00521-020-05165-2","volume":"32","author":"S Alonso","year":"2020","unstructured":"Alonso S, Mor\u00e1n A, P\u00e9rez D et al (2020) Estimating cooling production and monitoring efficiency in chillers using a soft sensor. Neural Comput Appl 32(23):17291\u201317308. https:\/\/doi.org\/10.1007\/s00521-020-05165-2","journal-title":"Neural Comput Appl"},{"key":"10560_CR4","doi-asserted-by":"publisher","first-page":"3265","DOI":"10.1007\/s00521-017-2901-3","volume":"30","author":"CAC Belchior","year":"2018","unstructured":"Belchior CAC, Ara\u00fajo RAM, Souza FAA et al (2018) Sensor-fault tolerance in a wastewater treatment plant by means of anfis-based soft sensor and control reconfiguration. Neural Comput Appl 30:3265\u20133276","journal-title":"Neural Comput Appl"},{"issue":"11","key":"10560_CR5","doi-asserted-by":"publisher","first-page":"4583","DOI":"10.1109\/JSEN.2018.2818886","volume":"18","author":"B Bidar","year":"2018","unstructured":"Bidar B, Shahraki F, Sadeghi J et al (2018) Soft sensor modeling based on multi-state-dependent parameter models and application for quality monitoring in industrial sulfur recovery process. IEEE Sens J 18(11):4583\u20134591. https:\/\/doi.org\/10.1109\/JSEN.2018.2818886","journal-title":"IEEE Sens J"},{"issue":"12","key":"10560_CR6","doi-asserted-by":"publisher","first-page":"5002","DOI":"10.1109\/JSEN.2018.2831445","volume":"18","author":"K Chhantyal","year":"2018","unstructured":"Chhantyal K, Jondahl MH, Viumdal H et al (2018) Upstream ultrasonic level based soft sensing of volumetric flow of non-newtonian fluids in open venturi channels. IEEE Sens J 18(12):5002\u20135013. https:\/\/doi.org\/10.1109\/JSEN.2018.2831445","journal-title":"IEEE Sens J"},{"key":"10560_CR7","doi-asserted-by":"publisher","unstructured":"Devore M, Gandhi N, Bateman AJ (2016) Virtual redundancy for safety assurance in the presence of sensor failures. In: AIAA Guidance, Navigation, and Control Conference. American Institute of Aeronautics and Astronautics, https:\/\/doi.org\/10.2514\/6.2016-0376","DOI":"10.2514\/6.2016-0376"},{"key":"10560_CR8","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.chemolab.2017.09.021","volume":"171","author":"Z Ge","year":"2017","unstructured":"Ge Z (2017) Review on data-driven modeling and monitoring for plant-wide industrial processes. Chemom Intell Lab Syst 171:16\u201325. https:\/\/doi.org\/10.1016\/j.chemolab.2017.09.021","journal-title":"Chemom Intell Lab Syst"},{"key":"10560_CR9","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.jprocont.2016.12.001","volume":"50","author":"JL Godoy","year":"2017","unstructured":"Godoy JL, Marchetti JL, Vega JR (2017) An integral approach to inferential quality control with self-validating soft-sensors. J Process Control 50:56\u201365. https:\/\/doi.org\/10.1016\/j.jprocont.2016.12.001","journal-title":"J Process Control"},{"key":"10560_CR10","doi-asserted-by":"publisher","unstructured":"Gonz\u00e1lez-Herb\u00f3n R, Rodr\u00edguez\u00a0Ossorio JR, Gonz\u00e1lez-Mateos G, et\u00a0al (2022) Control de caudal con un sensor virtual basado en t\u00e9cnicas de deep learning. In: XLIII Jornadas de Autom\u00e1tica, pp 368\u2013375, https:\/\/doi.org\/10.17979\/spudc.9788497498418.0368","DOI":"10.17979\/spudc.9788497498418.0368"},{"key":"10560_CR11","doi-asserted-by":"publisher","unstructured":"Gonz\u00e1lez-Herb\u00f3n R, Gonz\u00e1lez-Mateos G, Alonso S, et\u00a0al (2023) Virtual flow meter for an industrial process. In: International Conference on Engineering Applications of Neural Networks, Springer, pp 433\u2013444, https:\/\/doi.org\/10.1007\/978-3-031-34204-2_36","DOI":"10.1007\/978-3-031-34204-2_36"},{"key":"10560_CR12","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.isatra.2019.05.011","volume":"95","author":"R He","year":"2019","unstructured":"He R, Chen G, Dong C et al (2019) Data-driven digital twin technology for optimized control in process systems. ISA Trans 95:221\u2013234. https:\/\/doi.org\/10.1016\/j.isatra.2019.05.011","journal-title":"ISA Trans"},{"issue":"8","key":"10560_CR13","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. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput"},{"issue":"9","key":"10560_CR14","doi-asserted-by":"publisher","first-page":"2153","DOI":"10.1016\/j.engappai.2013.05.004","volume":"26","author":"PH Ibarg\u00fcengoytia","year":"2013","unstructured":"Ibarg\u00fcengoytia PH, Delgadillo MA, Garc\u00eda UA et al (2013) Viscosity virtual sensor to control combustion in fossil fuel power plants. Eng Appl Artif Intell 26(9):2153\u20132163. https:\/\/doi.org\/10.1016\/j.engappai.2013.05.004","journal-title":"Eng Appl Artif Intell"},{"issue":"11","key":"10560_CR15","doi-asserted-by":"publisher","first-page":"12868","DOI":"10.1109\/JSEN.2020.3033153","volume":"21","author":"Y Jiang","year":"2021","unstructured":"Jiang Y, Yin S, Dong J et al (2021) A review on soft sensors for monitoring, control, and optimization of industrial processes. IEEE Sens J 21(11):12868\u201312881. https:\/\/doi.org\/10.1109\/JSEN.2020.3033153","journal-title":"IEEE Sens J"},{"issue":"5","key":"10560_CR16","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/s00521-008-0218-y","volume":"18","author":"V Karri","year":"2008","unstructured":"Karri V, Ho TN (2008) Predictive models for emission of hydrogen powered car using various artificial intelligent tools. Neural Comput Appl 18(5):469\u2013476. https:\/\/doi.org\/10.1007\/s00521-008-0218-y","journal-title":"Neural Comput Appl"},{"issue":"5","key":"10560_CR17","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1080\/10789669.2011.573051","volume":"17","author":"H Li","year":"2011","unstructured":"Li H, Yu D, Braun JE (2011) A review of virtual sensing technology and application in building systems. HVAC &R Res 17(5):619\u2013645. https:\/\/doi.org\/10.1080\/10789669.2011.573051","journal-title":"HVAC &R Res"},{"key":"10560_CR18","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.jprocont.2020.03.012","volume":"89","author":"Y Liu","year":"2020","unstructured":"Liu Y, Xie M (2020) Rebooting data-driven soft-sensors in process industries: a review of kernel methods. J Process Control 89:58\u201373. https:\/\/doi.org\/10.1016\/j.jprocont.2020.03.012","journal-title":"J Process Control"},{"issue":"3","key":"10560_CR19","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s12599-021-00689-w","volume":"63","author":"D Martin","year":"2021","unstructured":"Martin D, K\u00fchl N, Satzger G (2021) Virtual sensors. Business & Inform Syst Eng 63(3):315\u2013323. https:\/\/doi.org\/10.1007\/s12599-021-00689-w","journal-title":"Business & Inform Syst Eng"},{"issue":"11","key":"10560_CR20","doi-asserted-by":"publisher","first-page":"3931","DOI":"10.3390\/s18113931","volume":"18","author":"CG Mattera","year":"2018","unstructured":"Mattera CG, Quevedo J, Escobet T et al (2018) A method for fault detection and diagnostics in ventilation units using virtual sensors. Sensors 18(11):3931. https:\/\/doi.org\/10.3390\/s18113931","journal-title":"Sensors"},{"key":"10560_CR21","doi-asserted-by":"publisher","first-page":"3609","DOI":"10.1007\/s00521-017-3301-4","volume":"31","author":"J Mendes","year":"2019","unstructured":"Mendes J, Souza F, Ara\u00fajo R et al (2019) Neo-fuzzy neuron learning using backfitting algorithm. Neural Comput Appl 31:3609\u20133618. https:\/\/doi.org\/10.1007\/s00521-017-3301-4","journal-title":"Neural Comput Appl"},{"key":"10560_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.pnucene.2020.103604","volume":"132","author":"SMH Mousakazemi","year":"2021","unstructured":"Mousakazemi SMH (2021) Comparison of the error-integral performance indexes in a GA-tuned PID controlling system of a PWR-type nuclear reactor point-kinetics model. Prog Nucl Energy 132:103604. https:\/\/doi.org\/10.1016\/j.pnucene.2020.103604","journal-title":"Prog Nucl Energy"},{"issue":"2","key":"10560_CR23","doi-asserted-by":"publisher","first-page":"160","DOI":"10.4995\/riai.2020.13611","volume":"18","author":"MA M\u00e1rquez-Vera","year":"2021","unstructured":"M\u00e1rquez-Vera MA, L\u00f3pez-Ortega O, Ramos-Velasco LE et al (2021) Diagn\u00f3stico de fallas mediante una LSTM y una red el\u00e1stica. Revista Iberoamericana de Autom\u00e1tica e Inform\u00e1tica industr 18(2):160\u2013171. https:\/\/doi.org\/10.4995\/riai.2020.13611","journal-title":"Revista Iberoamericana de Autom\u00e1tica e Inform\u00e1tica industr"},{"issue":"2","key":"10560_CR24","doi-asserted-by":"publisher","first-page":"317","DOI":"10.2166\/wst.2019.272","volume":"80","author":"AM Nair","year":"2019","unstructured":"Nair AM, Fanta A, Haugen FA et al (2019) Implementing an Extended Kalman Filter for estimating nutrient composition in a sequential batch MBBR pilot plant. Water Sci Technol 80(2):317\u2013328. https:\/\/doi.org\/10.2166\/wst.2019.272","journal-title":"Water Sci Technol"},{"issue":"3","key":"10560_CR25","doi-asserted-by":"publisher","first-page":"778","DOI":"10.3390\/s22030778","volume":"22","author":"P Peniak","year":"2022","unstructured":"Peniak P, R\u00e1stoon\u00fd K, Kan\u00e1likov\u00e1 A et al (2022) Simulation of virtual redundant sensor models for safety-related applications. Sensors 22(3):778. https:\/\/doi.org\/10.3390\/s22030778","journal-title":"Sensors"},{"key":"10560_CR26","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.ces.2013.02.069","volume":"96","author":"P Sagmeister","year":"2013","unstructured":"Sagmeister P, Wechselberger P, Jazini M et al (2013) Soft sensor assisted dynamic bioprocess control: efficient tools for bioprocess development. Chem Eng Sci 96:190\u2013198. https:\/\/doi.org\/10.1016\/j.ces.2013.02.069","journal-title":"Chem Eng Sci"},{"issue":"13","key":"10560_CR27","doi-asserted-by":"publisher","first-page":"10503","DOI":"10.1007\/s00521-021-06323-w","volume":"34","author":"JE Sierra-Garcia","year":"2021","unstructured":"Sierra-Garcia JE, Santos M (2021) Deep learning and fuzzy logic to implement a hybrid wind turbine pitch control. Neural Comput Appl 34(13):10503\u201310517. https:\/\/doi.org\/10.1007\/s00521-021-06323-w","journal-title":"Neural Comput Appl"},{"key":"10560_CR28","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.chemolab.2015.12.011","volume":"152","author":"FA Souza","year":"2016","unstructured":"Souza FA, Ara\u00fajo R, Mendes J (2016) Review of soft sensor methods for regression applications. Chemom Intell Lab Syst 152:69\u201379. https:\/\/doi.org\/10.1016\/j.chemolab.2015.12.011","journal-title":"Chemom Intell Lab Syst"},{"issue":"9","key":"10560_CR29","doi-asserted-by":"publisher","first-page":"5853","DOI":"10.1109\/TII.2021.3053128","volume":"17","author":"Q Sun","year":"2021","unstructured":"Sun Q, Ge Z (2021) A survey on deep learning for data-driven soft sensors. IEEE Trans Industr Inf 17(9):5853\u20135866. https:\/\/doi.org\/10.1109\/TII.2021.3053128","journal-title":"IEEE Trans Industr Inf"},{"key":"10560_CR30","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.conengprac.2017.09.015","volume":"70","author":"CM Th\u00fcrlimann","year":"2018","unstructured":"Th\u00fcrlimann CM, D\u00fcrrenmatt DJ, Villez K (2018) Soft-sensing with qualitative trend analysis for wastewater treatment plant control. Control Eng Pract 70:121\u2013133. https:\/\/doi.org\/10.1016\/j.conengprac.2017.09.015","journal-title":"Control Eng Pract"},{"issue":"8","key":"10560_CR31","doi-asserted-by":"publisher","first-page":"2941","DOI":"10.1080\/00207543.2018.1444806","volume":"56","author":"LD Xu","year":"2018","unstructured":"Xu LD, Xu EL, Li L (2018) Industry 4.0: state of the art and future trends. Int J Prod Res 56(8):2941\u20132962. https:\/\/doi.org\/10.1080\/00207543.2018.1444806","journal-title":"Int J Prod Res"},{"issue":"6","key":"10560_CR32","doi-asserted-by":"publisher","first-page":"2523","DOI":"10.1109\/TCST.2019.2929478","volume":"28","author":"X Yang","year":"2019","unstructured":"Yang X, Zhang Y, Shardt YA et al (2019) A KPI-based soft sensor development approach incorporating infrequent, variable time delayed measurements. IEEE Trans Control Syst Technol 28(6):2523\u20132531. https:\/\/doi.org\/10.1109\/TCST.2019.2929478","journal-title":"IEEE Trans Control Syst Technol"},{"issue":"2","key":"10560_CR33","doi-asserted-by":"publisher","first-page":"1508","DOI":"10.1109\/TIE.2017.2733443","volume":"65","author":"X Yuan","year":"2018","unstructured":"Yuan X, Wang Y, Yang C et al (2018) Weighted linear dynamic system for feature representation and soft sensor application in nonlinear dynamic industrial processes. IEEE Trans Industr Electron 65(2):1508\u20131517. https:\/\/doi.org\/10.1109\/TIE.2017.2733443","journal-title":"IEEE Trans Industr Electron"},{"issue":"5","key":"10560_CR34","doi-asserted-by":"publisher","first-page":"4404","DOI":"10.1109\/TIE.2020.2984443","volume":"68","author":"X Yuan","year":"2020","unstructured":"Yuan X, Li L, Shardt YA et al (2020) Deep learning with spatiotemporal attention-based lstm for industrial soft sensor model development. IEEE Trans Industr Electron 68(5):4404\u20134414. https:\/\/doi.org\/10.1109\/TIE.2020.2984443","journal-title":"IEEE Trans Industr Electron"},{"issue":"5","key":"10560_CR35","doi-asserted-by":"publisher","first-page":"4404","DOI":"10.1109\/TIE.2020.2984443","volume":"68","author":"X Yuan","year":"2021","unstructured":"Yuan X, Li L, Shardt YAW et al (2021) Deep learning with spatiotemporal attention-based LSTM for industrial soft sensor model development. IEEE Trans Industr Electron 68(5):4404\u20134414. https:\/\/doi.org\/10.1109\/TIE.2020.2984443","journal-title":"IEEE Trans Industr Electron"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10560-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10560-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10560-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T09:15:34Z","timestamp":1748682934000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10560-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":35,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10560"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10560-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"24 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2024","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 they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}