Preparation of TiO2 nanoparticles by the sol–gel method under different pH conditions and modeling of photocatalytic activity by artificial neural network

In this study, TiO2 nanoparticles were prepared by the sol–gel method under different pH conditions and the structural properties of TiO2 nanoparticles were obtained by X-ray diffraction and transmission electron microscopy. The photocatalytic activity of TiO2 nanoparticles was studied in the removal of C.I. Acid Red 27 (AR27) under UV light. The desired gelation pH for photocatalytic removal of AR27 was obtained at pH 5. At this pH, the predominant crystal phase of TiO2 is anatase and its crystallite size is smaller than at other gelation pHs. The artificial neural network (ANN) technique was applied to model and predict the photocatalytic activity of TiO2 nanoparticles prepared at the desired gelation pH. Four effective operational parameters were inserted as the inputs of the network and reaction rate constants (kap) were introduced as the outputs of the network. The results showed that the predicted data from the designed ANN model are in good agreement with the experimental data with a correlation coefficient (R2) of 0.9852 and mean square error of 0.00242. The designed ANN provides a reliable method for modeling the photocatalytic activity of TiO2 nanoparticles under different operational conditions. Furthermore, the relative importance of each operational parameter was calculated based on the connection weights of the ANN model. The initial dosage of TiO2 nanoparticles was the most significant parameter in the photocatalytic removal of AR27, followed by the UV-light intensity and initial AR27 concentration.