Comparative Study between Regression and Soft Computing Models to Maximize the Methane Storage Capacity of Anthracite-Based Adsorbents

Reliable prediction of n-heptane isomerization over Pt/(CrOx/ZrO2)-HMS via comparative assessment of regularization networks and surface response methodologies

Novel Pt–Cr/Zr(x)-HMS catalysts with different molar ratios of Cr/Zr were synthesized. These catalysts were characterized by necessary techniques including XRD, XRF, NH₃-TPD, FTIR, H₂ chemisorption, nitrogen sorption and TGA. Moreover, generalization performances of an optimized in-house regularization network and an RSM were compared for the prediction of activity and selectivity versus various molar ratios, feed temperatures and time on stream. The results indicated that the incorporation of Cr promotes the catalyst activity, in which a high amount of 63% conversion was obtained at Cr/Zr = 30 and T = 200 °C. Increasing temperature has an adverse effect on i-C₇ and mono plus multi-branch isomer selectivity nearly in all amounts of molar ratios. The best i-C₇ selectivity (66%), MOB (29.6%) and MUB (32%) were observed at 200 °C and Cr/Zr = 30. Although both modeling methods exhibited outstanding performances, statistical analysis revealed that optimized RN has slightly better performances than RSM.

Novel Pt–Cr/Zr(x)-HMS catalysts with different molar ratios of Cr/Zr were synthesized.