An integrated evolutionary approach for modelling and optimisation of CNC end milling process

In this research, a novel integrated evolutionary based approach is presented for the modelling and multi-objective optimisation of a machining process. Computer numerical control end milling process has been considered in the present work as it finds significant applications in diversified engineering industries. Firstly, genetic programming (GP) has been proposed for explicit formulation of non-linear relations between the machining parameters (spindle speed, feed and depth of cut) and the performance measures of interest (material removal rate and tool wear) using experimental data. Genetic programming approach optimises the complexity and size of the model during the evolutionary process itself and hence this technique has the potential to identify the true models avoiding the problems of conventional methods. Central composite second-order rotatable design had been utilised to plan the experiments and the effect of machining parameters on the performance measures is also reported. In the second part, as the chosen responses are conflicting in nature, a multi-objective optimisation problem has been formulated. A non-dominated sorting genetic algorithm-II (NSGA-II) has been used to simultaneously optimise the objective functions. The Pareto-optimal set generated is useful for process planning which is a critical link in computer-integrated manufacturing (CIM).