Application of Taguchi, ANFIS and grey relational analysis for studying, modeling and optimization of wire EDM process while using gaseous media

In the dry wire electrical discharge machining (WEDM) process, the liquid dielectric is replaced with gaseous medium to enhance the machining environment safety. Also, this modification improves the surface quality of machined specimen but decreases the material removal rate of the process. In the present work, experimental study of dry WEDM process has been performed while machining of Al/SiC metal matrix composite. At first, a series of exploratory experiments has been conducted to identify appropriate gas and wire material based on their cutting velocity. After selection of the best gas and best wire, they were used for later stage of experiments. At the next stage, experiment were designed and conducted based on L-27 Taguchi's orthogonal array to study the effect of pulse on time, pulse off time, gap voltage, discharge current, wire tension and wire feed on cutting velocity (CV) and surface roughness (SR). Analysis of variances (ANOVA) has been performed to identify significant factors. In order to correlate relationship between process inputs and responses, adaptive neuro-fuzzy inference system has been utilized. At the end, a grey relational analysis has been used to maximize CV and minimize SR simultaneously. Results indicated that oxygen gas and brass wire guarantee superior cutting velocity. Also according to ANOVA, pulse on time and current were found to have significant effect on CV and SR.