AccScience Publishing / AJWEP / Volume 19 / Issue 1 / DOI: 10.3233/AJW220011
RESEARCH ARTICLE

Modeling the Effect of Magnesia Nanoparticles on CO  Hydrogenation to Light Olefins in a Continuous Flow  Reactor Using Fine Gaussian Support Vector Machine

Alyaa K. Mageed1 Mohamed A. Abdel Ghany1 May Ali Alsaffar1* Jamal M. Ali1
Show Less
1 Department of Chemical Engineering, University of Technology, Iraq
AJWEP 2022, 19(1), 73–79; https://doi.org/10.3233/AJW220011
Submitted: 27 June 2021 | Revised: 19 July 2021 | Accepted: 19 July 2021 | Published: 19 January 2022
© 2022 by the Author(s. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

The effect of utilising energy derived from fossil sources on the environment has aroused research  interest in alternative and sustainable energy sources. Synthesis gas, a mixture of carbon monoxide (CO) and  hydrogen can be used as starting materials in hydrogenation reactions to produce chemical intermediates that can  be used in various processes. This study investigates the robustness of applying a fine Gaussian support vector  machine algorithm for predicting light olefins from catalytic CO hydrogenation using magnesia nanoparticlesbased catalysts. The datasets obtained from the CO hydrogenation reaction consist of input parameters such as  magnesia nanoparticles contents, reaction temperature, and reactor pressure, and the output parameters which  include CO conversions and the selectivity of light olefins (CH4, C2H6, C2H4 C3H8, C4H8, and C3H6). The dataset  was trained and employed for the prediction of the light olefins using a support vector machine with an inbuilt  Fine Gaussian Kernel function. The performance of the support vector machine was evaluated using the coefficient  of determination (R2 ), root mean squared error (RMSE), mean square error (MSE), and the mean absolute error  (MAE). The support vector machine showed significant potential in the prediction of CO conversion, CH4 selectivity,  C2H6 selectivity, and C2H4 selectivity as indicated by R2  of 0.770, 0.800, 0.730, and 0.930, respectively. While less  predictive performance was obtained for the prediction of C3H8 selectivity, C4H8 selectivity and C3H6 selectivity  as indicated by R2  of 0.630, 0.610, and 0.320, respectively.

Keywords
Support vector machine
CO hydrogenation
syngas
magnesia nanoparticles
light olefins
Conflict of interest
The authors declare they have no competing interests.
References

Atashi, H., Shiva, M., Farshchi Tabrizi, F. and A.A. Mirzaei  (2013). Study of syngas conversion to light olefins by  response surface methodology. Journal of Chemistry,  2013. https://doi.org/10.1155/2013/945735

Azapagic, A., Stamford, L., Youds, L. and C. BarteczkoHibbert (2016). Towards sustainable production and  consumption: A novel DEcision-Support Framework  IntegRating Economic, Environmental and Social  Sustainability (DESIRES). Computers & Chemical  Engineering, 91: 93-103. https://doi.org/https://doi. org/10.1016/j.compchemeng.2016.03.017

Bai, Y., Sun, Z., Zeng, B., Long, J., Li, L., de Oliveira, J.V.  and C. Li (2019). A comparison of dimension reduction  techniques for support vector machine modeling of multiparameter manufacturing quality prediction. Journal of  Intelligent Manufacturing, 30(5): 2245-2256. https://doi. org/10.1007/s10845-017-1388-1

Corma, A., Corresa, E., Mathieu, Y., Sauvanaud, L., AlBogami, S., Al-Ghrami, M. S. and A. Bourane (2017).  Crude oil to chemicals: Light olefins from crude oil.  Catalysis Science and Technology, 7(1): 12-46. https:// doi.org/10.1039/c6cy01886f

Fan, J., Wu, L., Zhang, F., Cai, H., Wang, X., Lu, X. and  Y. Xiang (2018). Evaluating the effect of air pollution  on global and diffuse solar radiation prediction using  support vector machine modeling based on sunshine  duration and air temperature. Renewable and Sustainable  Energy Reviews, 94: 732-747. https://doi.org/https://doi. org/10.1016/j.rser.2018.06.029

Ji, X., Shang, X., Dahlgren, R.A. and M. Zhang (2017).  Prediction of dissolved oxygen concentration in hypoxic  river systems using support vector machine: a case study  of Wen-Rui Tang River, China. Environmental Science  and Pollution Research, 24(19): 16062-16076. https://doi. org/10.1007/s11356-017-9243-7

Leong, W.C., Bahadori, A., Zhang, J. and Z. Ahmad (2021).  Prediction of water quality index (WQI) using support  vector machine (SVM) and least square-support vector  machine (LS-SVM). International Journal of River BasinManagement, 19(2): 149-156. https://doi.org/10.1080/157 15124.2019.1628030

Mohammadi, N., Samimi, A., Antalovits, F., Niedzwiecki,  L. and R. Mesbah (2021). Optimization of operating  conditions for CO hydrogenation to hydrocarbon via  response surface method. Chemical Methodologies, 5: 178-189. https://doi.org/10.22034/chemm.2021.122477

Pedersen, E.Ø., Svenum, I.-H. and E.A. Blekkan (2018). Mn  promoted Co catalysts for Fischer-Tropsch production  of light olefins – An experimental and theoretical study.  Journal of Catalysis, 361: 23-32. https://doi.org/https:// doi.org/10.1016/j.jcat.2018.02.011

Rădulescu, M., Rădulescu, S. and C.Z. Rădulescu (2009).  Sustainable production technologies which take into  account environmental constraints. European Journal of  Operational Research, 193(3): 730-740. https://doi.org/ https://doi.org/10.1016/j.ejor.2007.05.057

Shi, B., Zhang, Z., Liu, Y., Su, J., Liu, X., Li, X., Wang,  J., Zhu, M., Yang, Z., Xu, J. and Y.-F. Han (2020).  Promotional effect of Mn-doping on the structure and  performance of spinel ferrite microspheres for CO  hydrogenation. Journal of Catalysis, 381: 150-162. https:// doi.org/https://doi.org/10.1016/j.jcat.2019.10.034

Wang, Y., Zhao, Y., Liu, J., Li, Z., Waterhouse, G.I.N., Shi, R.,  Wen, X. and T. Zhang (2020). Manganese oxide modifiednickel catalysts for photothermal CO hydrogenation to  light olefins. Advanced Energy Materials, 10(5): 1-9.  https://doi.org/10.1002/aenm.201902860

Yang, Z., Zhang, Z., Liu, Y., Ding, X., Zhang, J., Xu, J. and Y.  Han (2021). Tuning direct CO hydrogenation reaction over  Fe-Mn bimetallic catalysts toward light olefins: Effects  of Mn promotion. Applied Catalysis B: Environmental,  285(November 2020): 119815. https://doi.org/10.1016/j. apcatb.2020.119815

Yuan, X., Tan, Q., Lei, X., Yuan, Y. and X. Wu (2017). Wind  power prediction using hybrid autoregressive fractionally  integrated moving average and least square support vector  machine. Energy, 129: 122-137. https://doi.org/10.1016/j. energy.2017.04.094

Zendehboudi, A., Baseer, M.A. and R. Saidur (2018).  Application of support vector machine models for  forecasting solar and wind energy resources: A review.  Journal of Cleaner Production, 199: 272-285. https://doi. org/https://doi.org/10.1016/j.jclepro.2018.07.164

Zhu, Y., Pan, X., Jiao, F., Li, J., Yang, J., Ding, M., Han, Y.,  Liu, Z. and X. Bao (2017). Role of manganese oxide in  syngas conversion to light olefins. ACS Catalysis, 7(4): 2800-2804. https://doi.org/10.1021/acscatal.7b00221

Share
Back to top
Asian Journal of Water, Environment and Pollution, Electronic ISSN: 1875-8568 Print ISSN: 0972-9860, Published by AccScience Publishing