Porosity Estimation of Mesoporous TiO2‐ZnO Nanocrystalline by Artificial Neural Network Modeling

Abstract

AbstractArtificial neural network was introduced for modeling and verifying the relative significance of operational variables to attain the best possible average pore diameter (Dp) of the mesoporous TiO2‐ZnO nanocrystalline synthesized by microwave‐assisted hydrothermal method. To optimize the system, the autonomous variables calcination temperature and concentrations of D‐glucose, polyethylene glycol, and Zn‐Ti were employed as input factors, Dp was designated as output. Dp was achieved from the implementation of the experimental model of the variables by the Barrett‐Joyner‐Halenda method. The network was trained by IBP, BBP, LM, QP, and GA algorithms as a model. The BBP‐4‐7‐1 model provided the optimum numerical properties among four other algorithms. Furthermore, the calcination temperature acted as the most efficient variable whilst D‐glucose concentration showed the least effect. By validating the microwave‐assisted hydrothermal conditions, in situ polymerization of poly(sodium 4‐styrene sulfonate) was introduced to activate mesopore walls by –SO3H functional groups used for ester production by transesterification of used cooking oil, resulting in a methyl ester content of 97.4 % and excellent reusability for ten sequential reactions without any further regeneration.