Wear Studies of AZ91-SiC/FA Composites using Taguchi Approach and Artificial Neural Networks (ANN) Fabricated by Stir-Casting
Abstract
In the present paper the impact of wear controlling factors on AZ91-SiC/Flyash reinforced composites fabricated by stir casting route is studied. The wear testing was done on pin on disc machine in dry conditions at three normal loads 10, 15, and 20 N with three sliding speeds 0.5, 1, and 1.5 m/s and three sliding distances 500, 750 and 1000 m. The experiments were conducted on full factorial design of experiments. The ANOVA technique was used to study the individual factors of friction coefficient and wear rate coupled with artificial neural networks (ANN) with single and multi-hidden layer models. Microstructures of worn surfaces were taken using scanning electron microscopy to predict the wear rate and to know the phenomenon on the surface. The artificial neural network model is found more accurate when compared with Taguchi approach.