Artificial neural network based optimization of a six-step two-bed pressure swing adsorption system for hydrogen purification

Liang Tong; Pierre Bénard; Yi Zong; Richard Chahine; Kun Liu; Jinsheng Xiao

doi:10.1016/j.egyai.2021.100075

Artificial neural network based optimization of a six-step two-bed pressure swing adsorption system for hydrogen purification

Liang Tong, Pierre Bénard, Yi Zong, Richard Chahine, Kun Liu, Jinsheng Xiao^*

^*Corresponding author for this work

Research output: Contribution to journal › Journal article › Research › peer-review

304 Downloads (Pure)

Abstract

The pressure swing adsorption (PSA) system is widely applied to separate and purify hydrogen from gaseous mixtures. The extended Langmuir equation fitted from the extended Langmuir-Freundlich isotherm has been used to predict the adsorption isothermal of hydrogen and methane on the zeolite 5A adsorbent bed. A six-step two-bed PSA model for hydrogen purification is developed and validated by comparing its simulation results with other works. The effects of the adsorption pressure, the P/F ratio, the adsorption step time and the pressure equalization time on the performance of the hydrogen purification system are studied. A four-step two-bed PSA model is taken into consideration, and the six-step PSA system shows higher about 13% hydrogen recovery than the four-step PSA system. The performance of the vacuum pressure swing adsorption (VPSA) system is compared with that of the PSA system, the VPSA system shows higher hydrogen purity than the PSA system. Based on the validated PSA model, a dataset has been produced to train the artificial neural network (ANN) model. The effects of the number of neurons in the hidden layer and the number of samples used for training ANN model on the predicted performance of ANN model are investigated. Then, the well-trained ANN model with 6 neurons in the hidden layer is applied to predict the performance of the PSA system for hydrogen purification. Multi-objective optimization of hydrogen purification system is performed based on the trained ANN model. The artificial neural network can be considered as a very effective method for predicting and optimizing the performance of the PSA system for hydrogen purification.

Original language	English
Article number	100075
Journal	Energy and AI
Volume	5
Number of pages	15
ISSN	2666-5468
DOIs	https://doi.org/10.1016/j.egyai.2021.100075
Publication status	Published - Sept 2021

Bibliographical note

Funding Information:
We wish to thank the financial support from the National Natural Science Foundation of China for the project No. 51476120, from the Natural Science Foundation of Liaoning Province for the project No. 2020-CSLH-43. Mr. Liang Tong also thanks the support from the China Scholarship Council (CSC) and the Fonds de Recherche du Québec - Nature et Technologies (FRQNT) for the PBEEE fellowship (No. 203790). Yi Zong also thanks to the International Network Programmne supported by the Danish Agency for Higher Education and Science (No. 8073-00026B) for the project PRESS- Proactive Energy Management Systems for Power-to-Heat and Power-to-Gas Solutions. We also appreciate Dr. Feng Ye for his assistance on artificial neural network programming.

Publisher Copyright:
© 2021 The Author(s)

Keywords

Artificial neural network
Hydrogen purification
Isotherm
Machine learning
Optimization
Pressure swing adsorption

Access to Document

10.1016/j.egyai.2021.100075

FulltextFinal published version, 2.23 MBLicence: CC BY

OpenUrl availability

Full text

Cite this

@article{f6a386262806460b81537ea9e6b4c8f0,

title = "Artificial neural network based optimization of a six-step two-bed pressure swing adsorption system for hydrogen purification",

abstract = "The pressure swing adsorption (PSA) system is widely applied to separate and purify hydrogen from gaseous mixtures. The extended Langmuir equation fitted from the extended Langmuir-Freundlich isotherm has been used to predict the adsorption isothermal of hydrogen and methane on the zeolite 5A adsorbent bed. A six-step two-bed PSA model for hydrogen purification is developed and validated by comparing its simulation results with other works. The effects of the adsorption pressure, the P/F ratio, the adsorption step time and the pressure equalization time on the performance of the hydrogen purification system are studied. A four-step two-bed PSA model is taken into consideration, and the six-step PSA system shows higher about 13% hydrogen recovery than the four-step PSA system. The performance of the vacuum pressure swing adsorption (VPSA) system is compared with that of the PSA system, the VPSA system shows higher hydrogen purity than the PSA system. Based on the validated PSA model, a dataset has been produced to train the artificial neural network (ANN) model. The effects of the number of neurons in the hidden layer and the number of samples used for training ANN model on the predicted performance of ANN model are investigated. Then, the well-trained ANN model with 6 neurons in the hidden layer is applied to predict the performance of the PSA system for hydrogen purification. Multi-objective optimization of hydrogen purification system is performed based on the trained ANN model. The artificial neural network can be considered as a very effective method for predicting and optimizing the performance of the PSA system for hydrogen purification.",

keywords = "Artificial neural network, Hydrogen purification, Isotherm, Machine learning, Optimization, Pressure swing adsorption",

author = "Liang Tong and Pierre B{\'e}nard and Yi Zong and Richard Chahine and Kun Liu and Jinsheng Xiao",

note = "Funding Information: We wish to thank the financial support from the National Natural Science Foundation of China for the project No. 51476120, from the Natural Science Foundation of Liaoning Province for the project No. 2020-CSLH-43. Mr. Liang Tong also thanks the support from the China Scholarship Council (CSC) and the Fonds de Recherche du Qu{\'e}bec - Nature et Technologies (FRQNT) for the PBEEE fellowship (No. 203790). Yi Zong also thanks to the International Network Programmne supported by the Danish Agency for Higher Education and Science (No. 8073-00026B) for the project PRESS- Proactive Energy Management Systems for Power-to-Heat and Power-to-Gas Solutions. We also appreciate Dr. Feng Ye for his assistance on artificial neural network programming. Publisher Copyright: {\textcopyright} 2021 The Author(s)",

year = "2021",

month = sep,

doi = "10.1016/j.egyai.2021.100075",

language = "English",

volume = "5",

journal = "Energy and AI",

issn = "2666-5468",

publisher = "Elsevier",

}

TY - JOUR

T1 - Artificial neural network based optimization of a six-step two-bed pressure swing adsorption system for hydrogen purification

AU - Tong, Liang

AU - Bénard, Pierre

AU - Zong, Yi

AU - Chahine, Richard

AU - Liu, Kun

AU - Xiao, Jinsheng

N1 - Funding Information: We wish to thank the financial support from the National Natural Science Foundation of China for the project No. 51476120, from the Natural Science Foundation of Liaoning Province for the project No. 2020-CSLH-43. Mr. Liang Tong also thanks the support from the China Scholarship Council (CSC) and the Fonds de Recherche du Québec - Nature et Technologies (FRQNT) for the PBEEE fellowship (No. 203790). Yi Zong also thanks to the International Network Programmne supported by the Danish Agency for Higher Education and Science (No. 8073-00026B) for the project PRESS- Proactive Energy Management Systems for Power-to-Heat and Power-to-Gas Solutions. We also appreciate Dr. Feng Ye for his assistance on artificial neural network programming. Publisher Copyright: © 2021 The Author(s)

PY - 2021/9

Y1 - 2021/9

N2 - The pressure swing adsorption (PSA) system is widely applied to separate and purify hydrogen from gaseous mixtures. The extended Langmuir equation fitted from the extended Langmuir-Freundlich isotherm has been used to predict the adsorption isothermal of hydrogen and methane on the zeolite 5A adsorbent bed. A six-step two-bed PSA model for hydrogen purification is developed and validated by comparing its simulation results with other works. The effects of the adsorption pressure, the P/F ratio, the adsorption step time and the pressure equalization time on the performance of the hydrogen purification system are studied. A four-step two-bed PSA model is taken into consideration, and the six-step PSA system shows higher about 13% hydrogen recovery than the four-step PSA system. The performance of the vacuum pressure swing adsorption (VPSA) system is compared with that of the PSA system, the VPSA system shows higher hydrogen purity than the PSA system. Based on the validated PSA model, a dataset has been produced to train the artificial neural network (ANN) model. The effects of the number of neurons in the hidden layer and the number of samples used for training ANN model on the predicted performance of ANN model are investigated. Then, the well-trained ANN model with 6 neurons in the hidden layer is applied to predict the performance of the PSA system for hydrogen purification. Multi-objective optimization of hydrogen purification system is performed based on the trained ANN model. The artificial neural network can be considered as a very effective method for predicting and optimizing the performance of the PSA system for hydrogen purification.

AB - The pressure swing adsorption (PSA) system is widely applied to separate and purify hydrogen from gaseous mixtures. The extended Langmuir equation fitted from the extended Langmuir-Freundlich isotherm has been used to predict the adsorption isothermal of hydrogen and methane on the zeolite 5A adsorbent bed. A six-step two-bed PSA model for hydrogen purification is developed and validated by comparing its simulation results with other works. The effects of the adsorption pressure, the P/F ratio, the adsorption step time and the pressure equalization time on the performance of the hydrogen purification system are studied. A four-step two-bed PSA model is taken into consideration, and the six-step PSA system shows higher about 13% hydrogen recovery than the four-step PSA system. The performance of the vacuum pressure swing adsorption (VPSA) system is compared with that of the PSA system, the VPSA system shows higher hydrogen purity than the PSA system. Based on the validated PSA model, a dataset has been produced to train the artificial neural network (ANN) model. The effects of the number of neurons in the hidden layer and the number of samples used for training ANN model on the predicted performance of ANN model are investigated. Then, the well-trained ANN model with 6 neurons in the hidden layer is applied to predict the performance of the PSA system for hydrogen purification. Multi-objective optimization of hydrogen purification system is performed based on the trained ANN model. The artificial neural network can be considered as a very effective method for predicting and optimizing the performance of the PSA system for hydrogen purification.

KW - Artificial neural network

KW - Hydrogen purification

KW - Isotherm

KW - Machine learning

KW - Optimization

KW - Pressure swing adsorption

U2 - 10.1016/j.egyai.2021.100075

DO - 10.1016/j.egyai.2021.100075

M3 - Journal article

AN - SCOPUS:85107143271

SN - 2666-5468

VL - 5

JO - Energy and AI

JF - Energy and AI

M1 - 100075

ER -

Artificial neural network based optimization of a six-step two-bed pressure swing adsorption system for hydrogen purification

Abstract

Bibliographical note

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this