Optimisation and Modelling of the Wear Properties of Laser-Coated SiC-Blend Ni Welds on Steel Substrates

Abstract

In the present work, a ceramic-metal matrix composite coating with the optimization and modelling of mechanical properties of Ni added SiC powders was studied on 45 steel by laser cladding. An artificial intelligent approach, which uses adaptive network fuzzy inference systems (ANFIS) based on experimental designs, is used to model the tribological behaviour of welds. An orthogonal array experiment is used and the effect of the deposition parameters on the welds is determined. Based on the average analysis and analysis of variance (ANOVA), four important factors are taken as inputs for the fuzzy logic inferences, while the loss of wear was taken as the output of the ANFIS. The welds are analysed using scanning electron microscopy (SEM) and wear tests are performed, using a pin-on-disk tribometer. This study identifies a group of highly developed needle-like dendrites and finer eutectic crystals, and lower wear volume loss is evident in the Ni-SiC welds. The ANFIS model based on Taguchi's design provides a better response pattern which shows extremely good fitting. As a result, satisfactory results are obtained between the predicted and experimental values of wear on laser coated Ni-added SiC welds, thereby validating the reliability and feasibility of this method.

Keywords

• silicon carbide
• anfis neural network
• wear properties
• metal matrix composite and laser cladding