Optimization of process parameters and performance for machining Inconel 718 in renewable dielectrics

Abstract

In this study, the optimization of processing parameters of Inconel 718 using electrical discharge machining (EDM) with three kinds of renewable dielectrics (soybean oil, sunflower seed oil, and rapeseed oil) was studied. As input process parameters, pulse current, pulse duration, duty ratio, and dielectric type were all utilized. The machining performance indices of EDM were material removal rate (MRR), surface roughness (Ra), energy pulse ratio per volume (EEV), and exhaust emission characteristics (EEC). The response surface method (RSM) was used to carry out the central composite design of the EDM experiment, and it looked into how process parameters affected machining performance. In addition, the extreme learning machine (ELM)-improved integrated beta-distribution cuckoo search (IBCS) algorithm was used to optimize the EDM process, and the optimization results were verified by experiments. The research results demonstrate that the predicted results are generally better than the experimental results, and the maximum and average deviations of the experimental results are within the acceptable range (maximum deviation <20%, average deviation <15%). The effectiveness of the optimization algorithm was proved, which was helpful in improving the performance of EDM, reducing energy consumption and emissions, and improving the sustainability of EDM.