Prediction of volume fraction of diamond deposition in Ni-diamond composite coatings - An artificial neural network approach

Abstract

Nickel-diamond composite coatings are produced by electro deposition using sedimentation techniques at various cathode current densities, pH and temperature. Electro deposition was carried out from a conventional Watts bath.Natural diamond powder of 6-12 µm size was used in this study .The volume fraction of diamond depo-sition in composite coated specimens were measured gravimetrically. An Artificial Neural Network (ANN) model was developed using 27 sample data obtained by designing an experiment with three level of experiment namely Low, Medium and High to predict the volume fraction of diamond deposition in Ni-diamond metal matrix. Within the range of input variables for the present case (pH = 2.5 to 4.5; current density (i) = 1 to 3 A/dm2; temperature = 30 to 60OC), the prediction capability of Artificial Neural Network(ANN) is very close to the experimental measurement of volume fraction of diamond deposition as the average errors in case of ANN is 0.00059%.