An integrated evolutionary approach for modelling and optimization of wire electrical discharge machining

Abstract

This paper presents an application of an integrated evolutionary approach for modelling and optimization of a wire electrical discharge machining (WEDM) process. The proposed methodology consists of two parts. In the first part, a novel application of genetic programming (GP) is proposed. GP is an evolutionary modelling algorithm which uses principles similar to genetic algorithms to model highly non-linear and complex processes, resulting in accurate and reliable models. Two important aspects of machining performance of WEDM, namely metal removal rate and surface roughness, are modelled based on experimental data using GP in terms of four prominent input variables. The effect of machining parameters on the performance measures is also reported. In the second part, as the chosen machining performances are opposite in nature, the problem under consideration is formulated as a multi-objective optimization problem and solved using an efficient evolutionary optimization algorithm, non-dominated sorting genetic algorithm-II (NSGA-II). The outcome of Pareto optimal solutions is presented. The work presents a fully fledged evolutionary approach for optimization of the process.