Prediction of gas storage capacities in metal organic frameworks using artificial neural network

• Published in: Microporous and mesoporous materials 2015-05, Vol.208, p.50-54
• Main Authors: Yıldız, Zeynep, Uzun, Harun
• Format: Article
• Language: English
• Subjects: Adsorption; Artificial neural network; Gas storage; MOFs
• ISSN: 1387-1811; 1873-3093
• DOI: 10.1016/j.micromeso.2015.01.037

In this study, artificial neural network was developed to forecast adsorption capacity of hydrogen gas in metal organic frameworks. Surface area, adsorption enthalpy, temperature and pressure were selected as input parameters. Hydrogen storage capacities of MOFs were computed using these four parameters. An artificial neural network was used to model the adsorption process. The prediction results were remarkably agreed with the experimental data. In this study, hydrogen adsorption capacities of different metal organic frameworks were predicted using artificial neural network. Artificial neural network was developed to forecast adsorption capacity of hydrogen gas in metal organic frameworks. The depending of adsorption capacity on surface area, adsorption enthalpy, temperature and pressure was studied. Hydrogen storage capacities of MOFs were computed using these four parameters. An artificial neural network was used to model the adsorption process. The prediction results were remarkably agreed with the experimental data. [Display omitted] •The gas adsorption capacities of MOFs were predicted using artificial neural network (ANN).•ANN modeling was performed using Matlab mathematical software by ANN toolbox.•The hydrogen gas storage capacities of MOFs were estimated successfully.•The best network configuration consisted of ten neurons in the hidden layer.