Multi-Objective Optimization of Surface Grinding Process Using NSGA II

The selection of optimum machining parameters in any machining process involves multiple conflicting objectives and often solution to such problems is sought by converting them into a single composite objective. In this paper a truly multi-objective optimization of the grinding process is carried out by considering both the objectives involved simultaneously, as against the classical approach used in earlier reported literature. The problem involves two conflicting objectives subjected to four constraints and ten process variables. The elitist non- dominated sorting genetic algorithm (NSGA II) is used to solve this multi-objective optimization problem. The Pareto-optimal front obtained is compared with earlier reported results, obtained using various non traditional optimization approaches. It is observed that all solutions in the Pareto- optimal fronts obtained by NSGA II dominate those reported earlier. Also the Pareto-optimal fronts obtained provide a wide range of trade-off operating conditions from which an appropriate operating point can be selected by the decision maker. Further a qualitative post-optimality analysis is performed to understand the relationships, if any, that exist among the optimum conditions obtained and the optimum values of the objective functions. On investigation it is observed that the Pareto-optimal solutions are affected by only four of the total ten process variables considered in the optimization study.