Artificial neural network modelling for average surface roughness in citrate stabilised electroless nickel boron coatings

Abstract

In this study, electroless nickel boron coatings were developed on Al 7075 aluminium alloy from the citrate stabilised electrolyte bath to investigate the applicability of artificial neural network (ANN) in the prediction of the average surface roughness Ra of the coatings. The process parameters such as concentrations of nickel, reducing agent and stabiliser were considered as input parameters and Ra was selected as an output parameter. Two different feed forward back propagation neural network architectures 3-10-1 and 3-5-5-1, were constructed and trained using Levenberg-Marquardt (LM) algorithm to predict the Ra. The accuracy of the networks was compared with the predicted coefficient of determination (R2) and mean squared error (MSE). The R2 and MSE of 0.9998 and 6.32E-05 were obtained for 3-5-5-1 against 0.9850 and 6.29 E-04 for 3-10-1 network architecture, which proved that the multi-layer perceptron (3-5-5-1) fits well for the experimental data presented.