A study on die sinking EDM of Nimonic C-263 super alloy : an intelligent approach to predict the process parameters using ANN

Abstract

In current study, machining characteristics of Nimonic C-263 are analysed by TAGUCHI and modelled using Artificial Neural Networks (ANN). The response parameters under consideration are Material Erosion Rate (MER), Electrode Wear Rate (EWR), Surface Roughness (SR) and Dimensional Overcut (DOC). A regression mathematical model is also developed to verify the capabilities of ANN. The modelling of ANN includes identifying appropriate combination of hidden layers and number of neurons in each hidden layer. Study on machining characteristics revealed, peak current as the most influential process parameters affecting all the responses; followed by Pulse on-time. A contrary effect is observed for Pulse off-time. A rare process parameter named flushing pressure showed negligible influence on responses. Among various ANN architectures, 6-6 architecture is noted to possess phenomenal prediction accuracy of 99.71% compared to 93.55% of regression analysis.

A review on conventional and nonconventional machining of Nickel-based Nimonic superalloy

“…Chekuri et al [102] predicted the process parameters of EDM of Nimonic C263 with the Cu-electrode by employing regression and ANN models. The analysis showed that IP was the most significant input parameter affecting the output parameters, viz., electrode wear rate, material erosion rate, SR, and dimensional overcut, followed by T on and T off .…”