Adaptive neuro-fuzzy interference system modelling of carbon nanotube-based electrical discharge machining process

Abstract

This study deals with modelling of surface roughness with carbon nanotube (CNT)-based electrical discharge machining (EDM) of AISI D2 tool steel material by means of adaptive neuro-fuzzy inference system (ANFIS) approach. The full factorial design of experimental techniques was adapted to conduct the experimental works. The CNT mixed dielectric nanofluids were prepared and used in the EDM process to analyze the surface roughness. The first-order sugeno type fuzzy interference modeling was used to predict the output parameters and compared with experimental values. The ANFIS model has been developed in terms of machining parameters for the prediction of surface roughness using trained data. The ANFIS predictions for the surface roughness with CNT the testing error was 0.20276 and correlation coefficient was 0.997 with the experimental data and for without CNT the testing error was 0.26529 and correlation coefficient was 0.889. The developed ANFIS model were compared in terms of their performances and shows that high residual R2 value indicate that the predicted model very well fits with the experimental data for using CNT on EDM process. The proposed model can also be used for estimating surface roughness on-line.