Taguchi’s DOE and artificial neural network analysis for the prediction of tribological performance of graphene nano-platelets filled glass fiber reinforced epoxy composites under the dry sliding condition

Abstract

For the present study, the tribological properties of glass-fibre reinforced epoxy (GFRE) composites and GFRE doped with 0.5 and 1 wt% of graphene nano-platelets (GNPs), were evaluated under the dry sliding condition by using pin-on-disc tribometer. Taguchi’s design of experiment (DOE) was applied to find the optimal parameters for minimum specific wear rate (SWR) and coefficient of friction (COF) which occurs at load of 40 N and GNP wt% of 1. The GNP wt% was the most significant factor determined by applying analysis of variance (ANOVA). An artificial neural network (ANN) model was developed for predicting the specific wear rate and coefficient of friction with a coefficient of determination (R2) equal to 0.965 and 0.986, respectively. Surface roughness, X-ray diffraction (XRD), Field-emission scanning electron microscope (FESEM) and Electron dispersive Spectroscopy (EDS) analysis of the worn specimen were conducted to examine surface morphology and the wear behaviour.