针对包含约束条件的工程优化问题,提出了基于人工蜂群的粒子群优化PSO-ABC算法.将PSO中较优的粒子作为ABC算法的蜜源,并使用禁忌表存储其局部极值,克服粒子群优化算法易陷入局部最优的缺陷.采用可行性规则进行约束处理,将粒子种群分为可行子群和不可行子群,并在ABC算法产生蜜源的过程中保留部分较优的可行解和不可行解的信息,弥补了可行性规则处理最优点位于约束边界附近的问题时存在的不足.四个典型工程优化设计的实验结果表明,该算法能够寻得更优的约束最优化解,且稳健性更强.%In order to solve engineering constrained optimization problems, this paper proposed a hybrid method combining particle swarm optimization(PSO) and artificial bee colony (ABC). The method selected the better particles in PSO as food sources for ABC algorithm, and used the tabu table to save the local optimization results in order to avoid PSO trapping into local optimum. And it used a feasibility-based rule to solve constrained problems, and divided the particle swarm into feasible subpopulation and infeasible subpopulation. So it produced the new food sources containing the information of good feasible and infeasible solution in the process of ABC, which could make up for the feasibility-based rule being invalid when the optimum was close to the boundary of constraint conditions. The algorithm was validated using four standard engineering design problems. The results indicate that PSO-ABC algorithm can find out better optimum and has stronger solidity.
展开▼
