Closed-loop optimization of catalysts for oxidative propane dehydrogenation with CO2 using artificial intelligence
Oxidative propane dehydrogenation with CO2 (ODPC) is an economical and ecofriendly process that produces propylene and consumes CO2 simultaneously. In this study, the catalyst composition for the ODPC reaction was optimized using a closed-loop optimization framework. A machine learning (ML) model wa...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-12-01
|
Series: | Journal of CO2 Utilization |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2212982023002317 |
_version_ | 1797506288637181952 |
---|---|
author | Jin-Soo Kim Iljun Chung Jungmok Oh Jisu Park Yongju Yun Jungho Shin Hyun Woo Kim Hyunju Chang |
author_facet | Jin-Soo Kim Iljun Chung Jungmok Oh Jisu Park Yongju Yun Jungho Shin Hyun Woo Kim Hyunju Chang |
author_sort | Jin-Soo Kim |
collection | DOAJ |
description | Oxidative propane dehydrogenation with CO2 (ODPC) is an economical and ecofriendly process that produces propylene and consumes CO2 simultaneously. In this study, the catalyst composition for the ODPC reaction was optimized using a closed-loop optimization framework. A machine learning (ML) model was trained to predict the propylene yield and CO2 conversion using an in-house experimental database obtained from metal oxide catalysts containing various elements. The trained ML model optimized the chemical composition of the catalysts and simultaneously maximized the propylene yield and CO2 conversion using a metaheuristic algorithm. The proposed catalysts were prepared and their ODPC performance was evaluated. The data were included in the initial database to retrain the ML model. After this closed-loop optimization for 4 cycles, the proposed catalysts, which comprised four or five metal components, exhibited an enhanced ODPC performance compared with that of the initial database, which contained up to three metal components. Density functional theory calculations and characterization techniques were performed to investigate the role of each metal in the proposed catalyst. This study suggested a framework to optimize the chemical composition of multi-component catalysts to enhance the propylene yield and CO2 activity in the ODPC reaction. |
first_indexed | 2024-03-10T04:30:31Z |
format | Article |
id | doaj.art-1d333e489eea4ad4a795903db2748d00 |
institution | Directory Open Access Journal |
issn | 2212-9839 |
language | English |
last_indexed | 2024-03-10T04:30:31Z |
publishDate | 2023-12-01 |
publisher | Elsevier |
record_format | Article |
series | Journal of CO2 Utilization |
spelling | doaj.art-1d333e489eea4ad4a795903db2748d002023-11-23T04:28:19ZengElsevierJournal of CO2 Utilization2212-98392023-12-0178102620Closed-loop optimization of catalysts for oxidative propane dehydrogenation with CO2 using artificial intelligenceJin-Soo Kim0Iljun Chung1Jungmok Oh2Jisu Park3Yongju Yun4Jungho Shin5Hyun Woo Kim6Hyunju Chang7Chemical Data-driven Research Center, Korea Research Institute of Chemical Technology (KRICT), 141 Gajeong-ro, Daejeon 34114, the Republic of KoreaDepartment of Chemical Engineering, Pohang University of Science and Technology (POSTECH), 77 Cheongam-ro, Pohang 37673, the Republic of KoreaDepartment of Chemical Engineering, Pohang University of Science and Technology (POSTECH), 77 Cheongam-ro, Pohang 37673, the Republic of KoreaDepartment of Chemical Engineering, Pohang University of Science and Technology (POSTECH), 77 Cheongam-ro, Pohang 37673, the Republic of KoreaDepartment of Chemical Engineering, Pohang University of Science and Technology (POSTECH), 77 Cheongam-ro, Pohang 37673, the Republic of Korea; Corresponding authors.Chemical Data-driven Research Center, Korea Research Institute of Chemical Technology (KRICT), 141 Gajeong-ro, Daejeon 34114, the Republic of KoreaChemical Data-driven Research Center, Korea Research Institute of Chemical Technology (KRICT), 141 Gajeong-ro, Daejeon 34114, the Republic of KoreaChemical Data-driven Research Center, Korea Research Institute of Chemical Technology (KRICT), 141 Gajeong-ro, Daejeon 34114, the Republic of Korea; Corresponding authors.Oxidative propane dehydrogenation with CO2 (ODPC) is an economical and ecofriendly process that produces propylene and consumes CO2 simultaneously. In this study, the catalyst composition for the ODPC reaction was optimized using a closed-loop optimization framework. A machine learning (ML) model was trained to predict the propylene yield and CO2 conversion using an in-house experimental database obtained from metal oxide catalysts containing various elements. The trained ML model optimized the chemical composition of the catalysts and simultaneously maximized the propylene yield and CO2 conversion using a metaheuristic algorithm. The proposed catalysts were prepared and their ODPC performance was evaluated. The data were included in the initial database to retrain the ML model. After this closed-loop optimization for 4 cycles, the proposed catalysts, which comprised four or five metal components, exhibited an enhanced ODPC performance compared with that of the initial database, which contained up to three metal components. Density functional theory calculations and characterization techniques were performed to investigate the role of each metal in the proposed catalyst. This study suggested a framework to optimize the chemical composition of multi-component catalysts to enhance the propylene yield and CO2 activity in the ODPC reaction.http://www.sciencedirect.com/science/article/pii/S2212982023002317Machine learningMetaheuristicsHeterogeneous catalysisCO2 utilizationOxidative alkane dehydrogenation |
spellingShingle | Jin-Soo Kim Iljun Chung Jungmok Oh Jisu Park Yongju Yun Jungho Shin Hyun Woo Kim Hyunju Chang Closed-loop optimization of catalysts for oxidative propane dehydrogenation with CO2 using artificial intelligence Journal of CO2 Utilization Machine learning Metaheuristics Heterogeneous catalysis CO2 utilization Oxidative alkane dehydrogenation |
title | Closed-loop optimization of catalysts for oxidative propane dehydrogenation with CO2 using artificial intelligence |
title_full | Closed-loop optimization of catalysts for oxidative propane dehydrogenation with CO2 using artificial intelligence |
title_fullStr | Closed-loop optimization of catalysts for oxidative propane dehydrogenation with CO2 using artificial intelligence |
title_full_unstemmed | Closed-loop optimization of catalysts for oxidative propane dehydrogenation with CO2 using artificial intelligence |
title_short | Closed-loop optimization of catalysts for oxidative propane dehydrogenation with CO2 using artificial intelligence |
title_sort | closed loop optimization of catalysts for oxidative propane dehydrogenation with co2 using artificial intelligence |
topic | Machine learning Metaheuristics Heterogeneous catalysis CO2 utilization Oxidative alkane dehydrogenation |
url | http://www.sciencedirect.com/science/article/pii/S2212982023002317 |
work_keys_str_mv | AT jinsookim closedloopoptimizationofcatalystsforoxidativepropanedehydrogenationwithco2usingartificialintelligence AT iljunchung closedloopoptimizationofcatalystsforoxidativepropanedehydrogenationwithco2usingartificialintelligence AT jungmokoh closedloopoptimizationofcatalystsforoxidativepropanedehydrogenationwithco2usingartificialintelligence AT jisupark closedloopoptimizationofcatalystsforoxidativepropanedehydrogenationwithco2usingartificialintelligence AT yongjuyun closedloopoptimizationofcatalystsforoxidativepropanedehydrogenationwithco2usingartificialintelligence AT junghoshin closedloopoptimizationofcatalystsforoxidativepropanedehydrogenationwithco2usingartificialintelligence AT hyunwookim closedloopoptimizationofcatalystsforoxidativepropanedehydrogenationwithco2usingartificialintelligence AT hyunjuchang closedloopoptimizationofcatalystsforoxidativepropanedehydrogenationwithco2usingartificialintelligence |