LAUSR

In this research, solvent based powder metallurgy is used to develop Silicon Carbide (SiC) doped reduced Graphene Oxide(r-GO) reinforced magnesium composite. SiC was doped with r-GO with varying wt.% (10 & 20) by adopting hydrothermal method. Influence of SiC doping over r-GO in wear resistance of developed composite was investigated by pin on disc method. Taguchi based Artificial neural network (ANN) was used to attain optimal wear parameter and to study the influence of wear parameter by developing a mathematical model. From ANOVA results it has been observed that wt.% of reinforcement play an important role in governing the wear loss of fabricated MMC. The developed ANN model exhibits accuracy of about 99.9% when subjected to predict the wear loss. Formation of tribolayer and plastic deformation were notified from worn surface morphology, thus evidencing for the occurrence of delamination and oxidation wear.