Optimization of Plating Processing, Microstructure and Properties of Ni–TiC Coatings Based on BP Artificial Neural Networks

Abstract

Ni–TiC composite coatings were prepared on substrate of aluminum alloy by pulse electrodeposition. The plating parameters for optimizing wear and corrosion resistance of Ni–TiC composite coatings were selected by orthogonal test, including the TiC particles concentration, current density, duty cycle, frequency and stirring rate. A three-layer back propagation (BP) artificial neural network with Lavenberg–Marquardt algorithm was established by MATLAB, which was used to train the network and predict orthogonal experimental data. Additionally, the best combination of parameters of the composite coatings were predicted and verified by experiments. The wear and corrosion resistance of Ni–TiC coatings were characterized and analyzed. The results indicated that the BP mode, which shows a relative error of approximately 3 %, could effectively predict the wear and corrosion resistance of Ni–TiC composite coatings. Ni–TiC composite coatings deposited by optimal synthetic condition showed dispersed TiC particles and continuous Ni matrix, as well as excellent wear and corrosion resistance.