Optimization of WEDM process of mould material using Kriging model to improve technological performances

Improving the technical performance of the wire electro-discharge machining (WEDM) process is an effective solution to decrease manufacturing costs. This paper addresses a multi-response optimization to simultaneously improve the cutting area rate CAR and decrease the kerf width AKW, while the average surface roughness ASR is predefined as a constraint. The processing conditions considered include the pulse-on time Ton, the current I, the voltage V and the wire speed S. A WEDM machine was adopted in conjunction with the Box–Behnken matrix to conduct experimental trials for machining of SKD61 steel. Highly nonlinear relationships between machining parameters and technological outputs were developed using the Kriging models. Finally, an archive-based micro-genetic algorithm (AMGA) was used to resolve the trade-off analysis among three responses and determine the optimal values of the processing factors. The results showed that a set of feasible solutions can be determined for the low kerf width as well as the surface roughness and the high cutting area rate. The selection of optimum parameters could help the WEDM operators to save the machining costs and time. The combination of the Kriging model and AMGA could be considered as an intelligent approach for modelling WEDM processes and predicting optimal results. © 2019, Indian Academy of Sciences.