Comparison of PSO, AGA, SA and Memetic Algorithms for Surface Grinding Optimization

Abstract

In striving to remain competitive in the global market, the concept of optimization of manufacturing processes has been extensively employed to meet the diverse production requirements. Optimization analysis of machining processes is usually based on either minimizing or maximizing certain objective functions. Recently, various non-traditional optimization techniques have evolved to optimize the process parameters of machining processes. The objective of this work is to study the effectiveness of the most commonly used non-traditional optimization methods as applied to a particular machining optimization problem. In this work, surface grinding processes are optimized using i) Particle Swarm Optimization (PSO) ii) Adaptive Genetic Algorithm (AGA) iii) Simulated Annealing (SA) and iv) Memetic algorithm (MA). Memetic algorithm used here has two variations as MA-1 and MA-2, each having the combination of PSO and SA and AGA and SA respectively. The mathematical model of surface grinding operations was adopted from a literature. A computer program was written in Visual C++ for the optimization computations. The computation results of various optimization methods are compared and it is observed that the results of PSO method have outperformed the results of other methods in terms of the combined objective function (COF).