Application of artificial neural networks to predict the grain size of nano-crystalline nickel coatings

• Published in: Computational materials science 2009-04, Vol.45 (2), p.499-504
• Main Authors: Rashidi, A.M., Eivani, A.R., Amadeh, A.
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Condensed matter: structure, mechanical and thermal properties; Cross-disciplinary physics: materials science; rheology; Exact sciences and technology; Grain size; Materials science; Nano-crystalline nickel coating; Nanocrystalline materials; Nanoscale materials and structures: fabrication and characterization; Nanoscale materials: clusters, nanoparticles, nanotubes, and nanocrystals; Physics; Structure of solids and liquids; crystallography
• ISSN: 0927-0256; 1879-0801
• DOI: 10.1016/j.commatsci.2008.11.016

In this paper, a feed-forwarded multilayer perceptron artificial neural network framework is used to model the dependence of the grain size of nano-crystalline nickel coatings on the process parameters namely current density, saccharin concentration and bath temperature. The process parameters were used as the model inputs and the resulting grain size of the nano-crystalline coating as the output of the model. The effect of the mentioned process parameters on the grain size of the deposited layer during the electroplating of nano-crystalline coatings from Watts-type bath was investigated using X-ray diffraction (XRD) technique. Comparison between the model predictions and the experimental observations predicted a remarkable agreement between them. The predictions of the model and sensitivity analysis showed that among the effective process parameters the current density has the most significant effect and the bath temperature has the smallest effect on the resulting grain size.