{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T08:34:46Z","timestamp":1775205286223,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:00:00Z","timestamp":1643241600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia","doi-asserted-by":"publisher","award":["."],"award-info":[{"award-number":["."]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Processes"],"abstract":"<jats:p>A misusage of machine learning (ML) strategies is usually observed in the process systems engineering literature. This issue is even more evident when dynamic identification is performed. The root of this problem is the gradient explode and vanishing issue related to the recurrent neural networks training. However, after the advent of deep learning, these issues were mitigated. Furthermore, the problem of data structuration is often overlooked during the machine learning model identification in this field. In this scenario, this work proposes a guideline for identifying ML models for the different applications in process systems engineering, which are usually for simulation or prediction purposes. While using the proposed guideline, the work also identifies a virtual analyzer for a pressure swing adsorption unit. In these types of adsorption separations, it is usual that the measurement of the main properties is not done online. Therefore, the virtual analyzer is another contribution of this manuscript. The overall results demonstrate that even though the test provides good performance during the ML model identification, its quality might degenerate over the application domain if the model application is overlooked.<\/jats:p>","DOI":"10.3390\/pr10020250","type":"journal-article","created":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T22:00:56Z","timestamp":1643320856000},"page":"250","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Machine Learning-Based Dynamic Modeling for Process Engineering Applications: A Guideline for Simulation and Prediction from Perceptron to Deep Learning"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0796-8116","authenticated-orcid":false,"given":"Carine M.","family":"Rebello","sequence":"first","affiliation":[{"name":"Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE\/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"},{"name":"Departamento de Engenharia Qu\u00edmica, Escola Polit\u00e9cnica (Polytechnic School), Universidade Federal da Bahia, Salvador 40210-630, Brazil"}]},{"given":"Paulo H.","family":"Marrocos","sequence":"additional","affiliation":[{"name":"Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE\/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1397-9628","authenticated-orcid":false,"given":"Erbet A.","family":"Costa","sequence":"additional","affiliation":[{"name":"Departamento de Engenharia Qu\u00edmica, Escola Polit\u00e9cnica (Polytechnic School), Universidade Federal da Bahia, Salvador 40210-630, Brazil"}]},{"given":"Vinicius V.","family":"Santana","sequence":"additional","affiliation":[{"name":"Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE\/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0715-4761","authenticated-orcid":false,"given":"Al\u00edrio E.","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE\/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"}]},{"given":"Ana M.","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE\/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0963-6449","authenticated-orcid":false,"given":"Idelfonso B. R.","family":"Nogueira","sequence":"additional","affiliation":[{"name":"Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE\/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2022,1,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kocijan, J., and Petelin, D. (2011). Output-error model training for gaussian process models. International Conference on Adaptive and Natural Computing Algorithms, Springer.","DOI":"10.1007\/978-3-642-20267-4_33"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1016\/0005-1098(95)00120-8","article-title":"Nonlinear black-box modeling in system identification: A unified overview","volume":"31","author":"Zhang","year":"1995","journal-title":"Automatica"},{"key":"ref_3","unstructured":"Koivisto, H. (1995). A Practical Approach to Model Based Neural Network Control, Tampere University of Technology."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1016\/S1474-6670(17)31273-9","article-title":"Nonlinear system identification with output error model through stabilized simulation","volume":"37","author":"Zhang","year":"2004","journal-title":"IFAC Proc. Vol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1177\/0954407011428720","article-title":"Braking torque control using reccurent neural networks","volume":"226","year":"2012","journal-title":"Proc. Inst. Mech. Eng. Part D J. Automob. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_7","unstructured":"Ruthven, D.M., Farooq, S., and Knaebel, K.S. (1994). Pressure Swing Adsorption, VCH Publishers."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"982934","DOI":"10.5402\/2012\/982934","article-title":"Advances in Pressure Swing Adsorption for Gas Separation","volume":"2012","author":"Grande","year":"2012","journal-title":"ISRN Chem. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5334","DOI":"10.1016\/j.ijhydene.2018.08.104","article-title":"Artificial neural network based optimization for hydrogen purification performance of pressure swing adsorption","volume":"44","author":"Ye","year":"2018","journal-title":"Int. J. Hydrogen Energy"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"100075","DOI":"10.1016\/j.egyai.2021.100075","article-title":"Artificial neural network based optimization of a six-step two-bed pressure swing adsorption system for hydrogen purification","volume":"5","author":"Tong","year":"2021","journal-title":"Energy AI"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.compchemeng.2017.05.006","article-title":"Machine learning model and optimization of a PSA unit for methane-nitrogen separation","volume":"104","author":"Anna","year":"2017","journal-title":"Comput. Chem. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"20412","DOI":"10.1021\/acs.iecr.9b04173","article-title":"Machine Learning-Based Multiobjective Optimization of Pressure Swing Adsorption","volume":"58","author":"Subraveti","year":"2019","journal-title":"Ind. Eng. Chem. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.engappai.2008.06.001","article-title":"Constructive learning neural network applied to identification and control of a fuel-ethanol fermentation process","volume":"22","author":"Meleiro","year":"2009","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Mouellef, M., Vetter, F.L., Zobel-Roos, S., and Strube, J. (2021). Fast and Versatile Chromatography Process Design and Operation Optimization with the Aid of Artificial Intelligence. Processes, 9.","DOI":"10.3390\/pr9122121"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Rahnama, A., Li, Z., and Sridhar, S. (2020). Machine Learning-Based Prediction of a BOS Reactor Performance from Operating Parameters. Processes, 8.","DOI":"10.3390\/pr8030371"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"119958","DOI":"10.1016\/j.energy.2021.119958","article-title":"Artificial-neural-network-based model predictive control to exploit energy flexibility in multi-energy systems comprising district cooling","volume":"222","author":"Coccia","year":"2021","journal-title":"Energy"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1016\/j.eng.2021.03.019","article-title":"Machine Learning in Chemical Engineering: Strengths, Weaknesses, Opportunities, and Threats","volume":"7","author":"Dobbelaere","year":"2021","journal-title":"Engineering"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"115801","DOI":"10.1016\/j.ces.2020.115801","article-title":"Modelling of a pressure swing adsorption unit by deep learning and artificial Intelligence tools","volume":"224","author":"Oliveira","year":"2020","journal-title":"Chem. Eng. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1008974908427","article-title":"A General Package for the Simulation of Cyclic Adsorption Processes","volume":"5","author":"Silva","year":"1999","journal-title":"Adsorption"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"4654","DOI":"10.1021\/acs.energyfuels.5b00975","article-title":"Syngas Purification by Porous Amino-Functionalized Titanium Terephthalate MIL-125","volume":"29","author":"Regufe","year":"2015","journal-title":"Energy Fuels"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"107344","DOI":"10.1016\/j.compchemeng.2021.107344","article-title":"Optimal fragrances formulation using a deep learning neural network architecture: A novel systematic approach","volume":"150","author":"Santana","year":"2021","journal-title":"Comput. Chem. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1939","DOI":"10.3390\/pr9111939","article-title":"A hybrid modeling framework for membrane separation processes: Application to lithium-ion recovery from batteries","volume":"9","author":"Regufe","year":"2021","journal-title":"Processes"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ljung, L. (1999). System Identification: Theory for the User, Prentice Hall PTR.","DOI":"10.1002\/047134608X.W1046"},{"key":"ref_24","first-page":"239","article-title":"A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code","volume":"21","author":"McKay","year":"1979","journal-title":"Technometrics"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"14037","DOI":"10.1021\/acs.iecr.0c01155","article-title":"Big Data-Based Optimization of a Pressure Swing Adsorption Unit for Syngas Purification: On Mapping Uncertainties from a Metaheuristic Technique","volume":"59","author":"Nogueira","year":"2020","journal-title":"Ind. Eng. Chem. Res."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"He, X., and Asada, H. (1993, January 2). A new method for identifying orders of input-output models for nonlinear dynamic systems. Proceedings of the 1993 American Control Conference, San Francisco, CA, USA.","DOI":"10.23919\/ACC.1993.4793346"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1007\/978-3-642-35289-8_26","article-title":"Practical Recommendations for Gradient-Based Training of Deep Architectures","volume":"7700","author":"Bengio","year":"2012","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_28","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"Li","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Bisong, E. (2019). Google colaboratory. Building Machine Learning and Deep Learning Models on Google Cloud Platform, Springer.","DOI":"10.1007\/978-1-4842-4470-8"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/0098-1354(95)00013-R","article-title":"Cross-validated structure selection for neural networks","volume":"20","author":"Schenker","year":"1996","journal-title":"Comput. Chem. Eng."}],"container-title":["Processes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9717\/10\/2\/250\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:08:56Z","timestamp":1760134136000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9717\/10\/2\/250"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,27]]},"references-count":30,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,2]]}},"alternative-id":["pr10020250"],"URL":"https:\/\/doi.org\/10.3390\/pr10020250","relation":{},"ISSN":["2227-9717"],"issn-type":[{"value":"2227-9717","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,27]]}}}