A Machine Learning Based Prediction of Machining Characteristics of Super Alloy in EDM Using Green Synthesized Nano Copper Oxide Dispersed Bio Dielectric Fluid

This present study describes the various machine learning techniques such as artificial neural network (ANN), and support vector machine (SVM) are used to predict and genetic algorithm (GA) is used to optimize the material removal rate (MRR) and surface roughness (SR) of Ti6Al4V in electrical discharge machining (EDM) by using nano copper oxide dispersed bio dielectric fluid. MRR and SR were estimated during EDM under the various operating parameters such as discharge voltage, current and discharge time. In this study, an optimal ANN architecture has been determined as 3-10-10-2 and SVM factors were altered by using grid search method. The predicted R-value of SVM is 0.9999 and the minimum mean absolute percentage error for MRR is 0.0085% and SR is 0.0564%. In addition to that, GA optimization has been employed by using objective function developed from Box-Behnken design and enhanced 6.41% and 16.94% in MRR and SR respectively.