LAUSR

A hybrid Al6061 composite material was fabricated with various weight percentage of different reinforcing material such as SiC, Al2O3, RHA and ZrSiO4 by liquid metallurgy route via. Stir casting method. The tribological properties were tested and carried out on pin-on-disc tribometers by considering various parameters like, mixture weight percentage of reinforcing materials, sliding distance, speed and applied load to study the tribological characteristics. Taguchi technique was used to analyse the wear rate of hybrid composites. Different experiments were conducted using Taguchi technique and the regression equations were developed through Analysis of Variance (ANOVA) to investigate the influence of various test parameters such as sliding distance, materials parameters (such as weight percentage of reinforcement), sliding distance and applied load. Finally, Taguchi results were used to train the Artificial Neural Network (ANN) model. The input parameters assigned to develop an ANN model are mixture weight percent of reinforcement, sliding distance, sliding speed and applied load. Finally confirmation test was done to verify the predictive model with the experimental results of the wear pin sample. The weight percentage of reinforcement had the greatest influence on statistical and physical properties of hybrid composites while the sliding speed exercised its impact on the Coefficient of Frication (COF) of hybrid composites on dry sliding wear and also on the optimal parameters for less wear rate and low COF. The results indicated that combination of 4.5 wt.% of reinforcement, 30 N load, 0.9 m/s sliding velocity and 3600 m sliding distance was the optimum blend for minimum wear rate and 4.5 wt.% of reinforcement, 3.4 m/s sliding velocity, 3600 m sliding distance and 40 N load was identified as the optimum blend for minimum COF using the main effect plot.