Hybrid Evolutionary Multi-Objective Optimization of Machining Parameters

Evolutionary multi-objective optimization (EMO) has received significant attention in recent studies in engineering design and analysis due to their flexibility, wide-spread applicability and ability to find multiple trade-off solutions. Optimal machining parameter determination is an important matter for ensuring an efficient working of a machining process. In this paper, we describe the use of an evolutionary multi-objective optimization (EMO) algorithm and a suitable local search procedure to optimize the machining parameters (cutting speed, feed, and depth of cut) in turning operations. We demonstrate the efficiency of our methodology through two case studies – one having two objectives and the other having three objectives. EMO solutions are modified using a local search procedure to achieve a better convergence property. Here, we also suggest a heuristic-based local search procedure for a computationally faster approach in which the problem-specific heuristics are derived from an innovization study performed on the EMO solutions. The methodology adopted in this paper can be used in other machining tasks or in other engineering design activities.