Abstract This study investigates the machining performance of Inconel 718 alloy using the die-sinking Electrical Discharge Machining (EDM) process, focusing on Material Removal Rate (MRR), Surface Roughness (SR), and surface morphology. Inconel 718, a nickel-based superalloy, is widely used in aerospace and high-temperature applications due to its excellent mechanical properties, but poses challenges to conventional machining. EDM offers a non-contact thermal erosion technique suitable for such hard-to-machine materials. A Taguchi-based Design of Experiments (DOE) approach was employed using an L27 orthogonal array to systematically explore the effects of five key input parameters: peak current, pulse-on time, pulse-off time, flushing pressure, and servo voltage. Experimental results revealed a maximum MRR of 0.312 g/min and a minimum SR of 1.932 µm under optimized parameter conditions. Surface integrity was further analyzed using Scanning Electron Microscopy (SEM), which showed characteristic features such as recast layers, microvoids, and globules due to the high-energy spark erosion. To enhance predictive capability, Artificial Neural Network (ANN) models were developed using three training algorithms: Levenberg–Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG). Among these, the BR algorithm outperformed the others, achieving the lowest Root Mean Square Error (RMSE) of 0.00121 for MRR and 0.00288 for SR, indicating superior prediction accuracy. This integrated study combining experimental design, surface characterization, and ANN modelling provides valuable insights into the machinability of Inconel 718 through EDM and offers a reliable framework for optimizing process parameters in precision manufacturing applications.
Kotha et al. (Thu,) studied this question.