Experimental investigation and development of a SVM model for hydrogenation reaction of carbon monoxide in presence of Co–Mo/Al2O3 catalyst

Abstract

In present paper, experimental investigation of Fischer–Tropsch synthesis in the presence of Co–Mo/Al2O3 catalyst in a batch autoclave reactor is carried out. The evaluation of this catalyst occurred at different temperature (423–623K) and over a pressure range of (10–50bar) with the H2/CO ratio varying from 2 to 6. This catalyst was found to be active, selective and very stable applying at high temperature and pressure. Also, the catalyst was characterized using XRD, FTIR and BET. By using this catalyst, 64% of the carbon monoxide was converted into methane at 1h of reaction and the rest of conversion occurred in the next 22h. Due to numerous of operating variables which affect the output process variables, proposing a mathematical model which can predict the synthesized gas composition that are CH4, CO2 and CO as a function of these variables could be very beneficial. Such predictive models are best suited in cases for which conventional reaction kinetics models cannot be developed. Therefore, support vector machine (SVM) as a new mathematical model has been applied for calculation/prediction of this synthesized gas composition of Fischer–Tropsch synthesis. The testing results from the SVM model are in very good agreement with experimental data. The minimum calculated squared correlation coefficient for estimated process variables is 0.98. Based on the results of this case study, SVM proved to be a reliable accurate estimation method.