Artificial neural network and regression modelling to study the effect of reinforcement and deformation on volumetric wear of red mud nano particle reinforced aluminium matrix composites synthesized by stir casting

Abstract

Artificial neural network (ANN) approach was used for the prediction of effect of reinforcement and deformation on volumetric wear of red mud nano particle reinforced aluminium matrix composites synthesized by stir casting. Red mud obtained from alumina processing industry was milled in a high energy ball mill and the particle size was reduced to 40nm in 30h. Sliding wear characteristics of the composites were evaluated on pin on disc wear tester at different loads of 10N, 20N and 30N and sliding speeds of 200, 400, and 600RPM. The wear rate of the composite was decreased with increase in weight fraction of red mud up to 10% and beyond that the wear rate was increased. The interfacial area between the matrix and the reinforcement increases with increase in red mud volume fraction, leading to increase in strength and wear resistance. Mathematical regression model and ANN model have been developed to predict theoretical wear rate of the composite and observed that ANN predictions have excellent agreement with measured values than other models. Thus, the prediction of wear rate of the nano composites using artificial neural network before actual manufacture will considerably saves the project time, effort and cost.