Process optimization of preparing spherical titania colloids with uniform distribution using artificial neural networks

Optimal operating variables for preparing submicron uniform titania colloids were estimated using the artificial neural networks (ANN) modeling and the process optimization algorithms. Titania colloids were synthesized by a sol–gel method using mixture recipes of titanium tetraisopropoxide (TTIP), NH3, and H2O with ethanol/acetonitrile under temperature-controlled conditions. Different sets of the operating variables, such as [NH3], [H2O], and reaction temperature, were selected within an operating range to carry out Design of Experiment to evaluate the prepared particle size (PS) and the particle size distribution (PSD) data. The relationship between the operating variables and PS and PSD of the prepared samples can be constructed by an ANN modeling approach. The built ANN model was then used to predict PS and PSD values corresponding to the operating variables. The optimal operating conditions to fabricate different PS values with narrow PSD were determined by the ANN model with the optimization method. Meanwhile, the monodispersed colloids between 150 and 400 nm were fabricated using the determined optimal operating conditions.