LAUSR

Abstract This study discusses the experimental investigation on WEDM of combustor material (i.e. nimonic 263). Experimentation has been executed by varying pulse-on time (Ton), pulse-off time (Toff), peak current (Ip) and spark gap voltage (Sv). The influence of these parameters was studied on the Surface roughness parameters (i.e., average: Ra and ten-point mean: Rz), recast layer thickness (RLT), and changes in the machined surface. Experiments are designed as per Box-Behnken design technique. Parametric optimization has also been performed using response surface methodology. The results of proposed algorithm show that the BPNN is effective tool for the prediction of responses. The BPNN predicted results are 99% in agreement with the experimental results. Furthermore, microstructure and composition of WEDMed surface was assessed by FE-SEM. It was observed that WEDMed surfaces contain micro-cracks, craters, spherical droplets and lump of debris. Longer pulse-on time causes greater discharge energy, hence leading to higher material removal rate, surface roughness, and recast layer thickness. In addition, the mechanism of recast layer formation and microhardness of machined surfaces have been critically evaluated to apprehend better understanding of the technique. Furthermore, polishing was considered as a post-processing technique for removing the RLT. The key features of experimental procedure are also highlighted.