Prediction of the relative texture coefficient of nanocrystalline nickel coatings using artificial neural networks

Abstract

In this paper, the relative texture coefficient (RTC) of nanocrystalline (NC) nickel as a function of electroplating parameters has been modeled using artificial neural network (ANN). In the model, the inputs are the electroplating parameters namely current density, concentration of sodium saccharin in bath and plating temperature. In order to train and test the ANN model with a consistent set of experimental data, NC nickel coatings has been provided using a Watts-type bath, in which the significant parameters such as current density, concentration of sodium saccharin in bath and plating temperature have been systematically varied. The RTC has been determined using the peak intensities of diffracted x-ray radiation from (hkl) crystallographic planes of deposits with respect to coarse grained nickel (reference sample). An excellent agreement between the model predictions and the experimental data was obtained indicating that the ANN approach can be used as a reliable and accurate tool for prediction of the RTC of NC nickel coatings.