A fast and elitist multiobjective genetic algorithm: NSGA-II
IEEE Transactions on Evolutionary Computation
Hi-index | 0.00 |
Because of their numerous and diverse ranges, the tuning of process parameters of a machining process depends heavily upon operators' technologies and experiences. Still, proper tuning cannot be expected from such a manual process, which encourages the use of an optimization tool for effective utilization of a process. In this paper, a multi-objective genetic algorithm (GA) is applied to electrochemical machining for tuning its various process parameters so that the optimum output can be achieved. An experimental dataset is used for modeling the problem through regression analysis, and then the GA is applied to a linear model and an exponential model for maximizing material removal rate and minimizing surface roughness.