Optimizing CNC Turning Process Using Real Coded Genetic Algorithm and Differential Evolution
This paper proposes the applications of non-traditional stochastic optimization techniques as real coded genetic algorithm namely ”LXPM” and Differential Evolution(DE) for determination of optimal machining conditions for turning process on Computer Numerically Controlled (CNC) machines. The problem, discussed in the present study comprises several nonlinear constraints with an optimum criteria based on minimizing total production time that affects the production rate as well. The various constraints arise due to restricted machining features and are imposed on cutting force, power, tool-chip interface temperature and surface. The determination of optimal cutting parameters has significant importance for economic machining and plays an important role in reducing machining errors as tool breakage, tool wear, tool chatter etc. as well. The performances of employed heuristics are compared with several other optimization methods available in literature. The computational results demonstrate convincingly, the reliability and efficiency of considered methods for predicting optimal machining conditions for achieving the desired goal.