Abstract

An artificial-neural-network (ANN) model is developed for the analysis and prediction of correlations between processing planetary milling parameters and the crystallite size of ZnO nanopowder by applying the back-propagation (BP) neural network technique. The input parameters of the BP network are rotation speed and ball-to-powder weight ratio. The nanopowder was synthesized by planetary mechanical milling and the required data for training were collected from the experimental results. The synthesized ZnO nanoparticles were characterized by X-ray diffraction (XRD) and Scanning Electron Microcopy (SEM). The crystallite size and internal strain were evaluated by XRD patterns using Williamson – Hall method. It was found that, artificial neural network was very effective providing a perfect agreement between the outcomes of ANN modeling and experimental results. An optimization model is then developed through the analysis on the evaluated network response surface and contour plots to find the best milling parameters (rotation speed and balls to powder ratio) producing the minimal average crystallite size.

Key words: Milling, optimization, neural network, ZnO.