Evaluating Process Parameters of Multi-Pass Turning Process Using Hybrid Genetic Simulated Swarm Algorithm

Abstract

Evolutionary computation is one of the important problems solving method frequently used by the researchers. The choice of an algorithm to optimize the problem is determined by some sort of reliability of the researcher with that technique. To overcome the limitations in individual algorithms and to achieve synergic effects, fusion or hybridization of two or more algorithms is carried out. Hybrid algorithms have gained popularity because there is no evidence that a universal optimal strategy exists for solving optimization problems. In this work, a hybrid algorithm called hybrid genetic simulated swarm (HGSS) algorithm is proposed to optimize the parameters of multi-pass turning operation. The HGSS algorithm is a fusion of genetic algorithm (GA), simulated annealing (SA) and particle swarm optimization (PSO) algorithms. The objectives of this work are (i) to explore and exploit the problem search space through hybridization, (ii) to justify that proficient hybridization of evolutionary algorithms (EAs) will yield an efficient means to solve the optimization problems. In this work, the EAs such as GA, SA and PSO are also applied to optimize parameters and results are compared with HGSS. The results of the proposed work HGSS are very effective than other algorithms.