【摘要】 针对人工蜂群算法收敛速度缓慢、容易陷入局部最优解的问题,将改进的遗传进化机制与蜂群算法相融合,提出了一种遗传蜂群算法。通过引入遗传算法的交叉变异算子,有效地增加了食物源的多样性,减小陷入局部最优的可能;采用了自适应选择食物源的机制,使蜂群在中后期更好地搜索到最优食物源所在区域,进而提高了全局搜索效率;此外,提出了在侦察蜂阶段的局部搜索策略,提高了算法进化的收敛速度。将遗传蜂群算法应用于TSP中,通过对TSBLIB中几个典型问题的实验,结果表明,提出的遗传蜂群算法具有很强的全局优化能力,在求解TSP问题中精度高,收敛速度快,且是一种解决TSP问题的有效方法。更多还原

【Abstract】 In order to overcome the problem of the slow convergence and falling into local optimum easily in artificial bee colony algorithm,a new algorithm called genetic bee colony algorithm is proposed,and it is a fusion of the improved genetic evolution mechanism and artificial bee colony algorithm. Artificial bee colony algorithm can increase the diversity of food source by leading into the crossover and mutation operator of genetic algorithm,and it can reduce the possibility of falling into local optimum. The mechanism of adaptive selection for bees is used in this paper. Bees can search near the best food source by introducing the strategy of adaptive selection in the middle and late stage,thus the efficiency of the global search is better improved. Furthermore,a local searching strategy is proposed to improve the convergence rate of evolution at the scout stage. The genetic bee colony algorithm is applied to TSP,and experimental results by several typical problems of the TSPLIB show that the genetic bee colony algorithm has a strong ability of global optimization. In the process of solving TSP,the genetic bee colony algorithm has high precision and fast convergence speed,and it is a more effective method for solving TSP problem.更多还原