Wear performance analysis and optimization of process parameters of novel AA7178/nTiO2 using ANN-GRA method

Abstract

The current research investigates the microstructural and wear behaviour of nano TiO2 particles with concentrations of 1%, 2%, and 3%, which were reinforced with an AA7178 metal matrix composite using a stir casting method. Artificial Neural Network (ANN) and Grey Relational Analysis (GRA) methods were used to model the wear characteristics and attain the optimal values of the input process parameters such as load, sliding speed, nanoparticles’ weight percentage, and sliding distance. An L16 orthogonal array was used for the design of the experiment. An investigation of the variance of grey relationship grade revealed that the wt.% of nano-size TiO2 particle had a substantial impact on both the friction coefficient and wear rate i.e.,70.30%. Analysis of the nano-composite's wear behaviour was carried out effectively using an ANN model. The main reason for the worn-out surface was micro-cutting and micro-ploughing, as evidenced by scanning electron microscope (SEM) micrographs obtained at load (40 N), weight percentage of nano TiO2 (3 wt.%), sliding speed (1 m/s) and sliding distance (2000 m).