Artificial Neural Network technique to assess tribological performance of GFRP composites incorporated with graphene nano-platelets

Abstract

For the present study, glass fibre reinforced polymer (GFRP) composites and GFRP composites incorporated with 0.5 wt% and 1 wt% of graphene nano-platelets (GNPs) were prepared by hand lay-up method, coupled with compression moulding. The tribological testing was conducted in dry-sliding environment with a Pin-on-disc Tribo-Tester for a running time of 10 min and under applied load of 20 N, 40 N, 60 N and 80 N. The experiment data (610 data sets) were used while applying the Artificial Neural Network (ANN) technique. The experiment results were compared with the results obtained from the ANN. It showed that the ANN predicted the output parameters with an overall percentage error of less than 5%. ANN predicted wear for all three composite samples had the mean square error (MSE) less than 2.2005×10−2 and the coefficient of determination (R2) greater than 99 %, whereas the ANN predicted coefficient of friction for all three composite samples had the MSE less than 5.057×10−5 and R2 greater than 90 %. During the course of the present investigation, the Field-emission Scanning Electron Microscope (FESEM) and Energy-dispersive X-ray Spectroscopy (EDS) analysis were also used to examine the wear mechanism.