Development of a Neural Network Model and Taguchi-Based Optimization for Dry Sliding Wear Performance of Al 6065 Alloy Reinforced with Nano SiC and Graphene Nanoplatelets

Abstract

The Al6065 alloy is widely used in various applications, including tubing for furniture, railway and bus structures, pylons, platforms, and pipelines. However, due to the wear experienced in these applications, it is essential to enhance the wear confrontation of this alloy. To address this issue, this research focuses on reinforcing Al6065 with nanoparticles of silicon carbide and graphene by means of the stir casting method. The wear behaviour of the alloy is studied by varying the rotational speed, load, and composition of reinforcement in the stir casting machine using Taguchi design of experiment. The rate of wear and friction coefficient are measured as responses. The obtained results are then analysed and optimized for the minimum of the output responses using S/N ratio analysis. Further, ANOVA is carried out to determine the influence of each parameter, and a model of the neural network is developed to predict the response. The findings indicate that cumulative the percentage of reinforcement enhances the wear resistance of the alloy. The optimized values of the rotational speed, load, and composition of reinforcement lead to improved wear resistance, with a corresponding decrease in the coefficient of friction. The ANOVA results reveal that the rotational speed and load significantly affect the responses, while the reinforcement composition has a moderate effect. The developed neural network model accurately predicts the response with a high degree of accuracy. The model can be used to optimize the wear behaviour of Al6065 alloy reinforced with nanoparticles of silicon carbide and graphene, as well as for prediction of the alloy's wear behaviour in various application environments. In conclusion, this research delivers a complete thoughtful of the wear behaviour of Al6065 alloy reinforced with nanoparticles of silicon carbide and graphene. The findings can be used to optimize the wear resistance and improve the routine of this alloy in various applications.