TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Modelling of a pressure swing adsorption unit by deep learning and artificial Intelligence tools

Tutkimustuotosvertaisarvioitu

Standard

Modelling of a pressure swing adsorption unit by deep learning and artificial Intelligence tools. / Oliveira, Luís Miguel Cunha; Koivisto, Hannu; Iwakiri, Igor G.I.; Loureiro, José M.; Ribeiro, Ana M.; Nogueira, Idelfonso B.R.

julkaisussa: Chemical Engineering Science, Vuosikerta 224, 115801, 2020.

Tutkimustuotosvertaisarvioitu

Harvard

Oliveira, LMC, Koivisto, H, Iwakiri, IGI, Loureiro, JM, Ribeiro, AM & Nogueira, IBR 2020, 'Modelling of a pressure swing adsorption unit by deep learning and artificial Intelligence tools', Chemical Engineering Science, Vuosikerta. 224, 115801. https://doi.org/10.1016/j.ces.2020.115801

APA

Oliveira, L. M. C., Koivisto, H., Iwakiri, I. G. I., Loureiro, J. M., Ribeiro, A. M., & Nogueira, I. B. R. (2020). Modelling of a pressure swing adsorption unit by deep learning and artificial Intelligence tools. Chemical Engineering Science, 224, [115801]. https://doi.org/10.1016/j.ces.2020.115801

Vancouver

Oliveira LMC, Koivisto H, Iwakiri IGI, Loureiro JM, Ribeiro AM, Nogueira IBR. Modelling of a pressure swing adsorption unit by deep learning and artificial Intelligence tools. Chemical Engineering Science. 2020;224. 115801. https://doi.org/10.1016/j.ces.2020.115801

Author

Oliveira, Luís Miguel Cunha ; Koivisto, Hannu ; Iwakiri, Igor G.I. ; Loureiro, José M. ; Ribeiro, Ana M. ; Nogueira, Idelfonso B.R. / Modelling of a pressure swing adsorption unit by deep learning and artificial Intelligence tools. Julkaisussa: Chemical Engineering Science. 2020 ; Vuosikerta 224.

Bibtex - Lataa

@article{700bc2dba1a948929f13d39ddf20a7ba,
title = "Modelling of a pressure swing adsorption unit by deep learning and artificial Intelligence tools",
abstract = "Syngas is one of the main sources available for the production of pure H2 and synthetic fuels, among others. Pressure swing adsorption (PSA) is considered to be an efficient alternative for pre-treatment of syngas. However, it displays very complex dynamical behaviour. This work proposes the development of different Artificial Intelligence based models for the prediction of the dynamic behaviour of several process output variables. A classical model of ANNs, a machine learning model and a deep learning model was here developed. It was found that Deep Learning networks were the only ones capable of fully representing the dynamic behaviour of the PSA unit, whereas the other models were only partially capable of predicting it. Thus, it is proposed a reliable real-time soft sensor for a PSA unit based on Deep Leaning strategy. This strategy provides bases to overtake several problems associated to this processes control, operation and optimization.",
keywords = "Artificial intelligence, Artificial neural networks, Deep learning, Machine learning, Pressure swing adsorption, Syngas",
author = "Oliveira, {Lu{\'i}s Miguel Cunha} and Hannu Koivisto and Iwakiri, {Igor G.I.} and Loureiro, {Jos{\'e} M.} and Ribeiro, {Ana M.} and Nogueira, {Idelfonso B.R.}",
note = "EXT={"}Nogueira, Idelfonso B.R.{"}",
year = "2020",
doi = "10.1016/j.ces.2020.115801",
language = "English",
volume = "224",
journal = "Chemical Engineering Science",
issn = "0009-2509",
publisher = "Elsevier",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Modelling of a pressure swing adsorption unit by deep learning and artificial Intelligence tools

AU - Oliveira, Luís Miguel Cunha

AU - Koivisto, Hannu

AU - Iwakiri, Igor G.I.

AU - Loureiro, José M.

AU - Ribeiro, Ana M.

AU - Nogueira, Idelfonso B.R.

N1 - EXT="Nogueira, Idelfonso B.R."

PY - 2020

Y1 - 2020

N2 - Syngas is one of the main sources available for the production of pure H2 and synthetic fuels, among others. Pressure swing adsorption (PSA) is considered to be an efficient alternative for pre-treatment of syngas. However, it displays very complex dynamical behaviour. This work proposes the development of different Artificial Intelligence based models for the prediction of the dynamic behaviour of several process output variables. A classical model of ANNs, a machine learning model and a deep learning model was here developed. It was found that Deep Learning networks were the only ones capable of fully representing the dynamic behaviour of the PSA unit, whereas the other models were only partially capable of predicting it. Thus, it is proposed a reliable real-time soft sensor for a PSA unit based on Deep Leaning strategy. This strategy provides bases to overtake several problems associated to this processes control, operation and optimization.

AB - Syngas is one of the main sources available for the production of pure H2 and synthetic fuels, among others. Pressure swing adsorption (PSA) is considered to be an efficient alternative for pre-treatment of syngas. However, it displays very complex dynamical behaviour. This work proposes the development of different Artificial Intelligence based models for the prediction of the dynamic behaviour of several process output variables. A classical model of ANNs, a machine learning model and a deep learning model was here developed. It was found that Deep Learning networks were the only ones capable of fully representing the dynamic behaviour of the PSA unit, whereas the other models were only partially capable of predicting it. Thus, it is proposed a reliable real-time soft sensor for a PSA unit based on Deep Leaning strategy. This strategy provides bases to overtake several problems associated to this processes control, operation and optimization.

KW - Artificial intelligence

KW - Artificial neural networks

KW - Deep learning

KW - Machine learning

KW - Pressure swing adsorption

KW - Syngas

U2 - 10.1016/j.ces.2020.115801

DO - 10.1016/j.ces.2020.115801

M3 - Article

VL - 224

JO - Chemical Engineering Science

JF - Chemical Engineering Science

SN - 0009-2509

M1 - 115801

ER -