论文部分内容阅读
提出一种基于随机黑洞粒子群算法(RBH-PSO)和逐步淘汰策略的多目标粒子群优化(MRBHPSO-SE)算法.利用RBH-PSO全局优化能力强和收敛速度快的优点逼近Pareto最优解;为了避免拥挤距离排序策略的缺陷,提出逐步淘汰策略,并将其应用到下一代粒子的选择策略中.同时,动态选择领导粒子,运用动态惯性权重系数和变异操作来增强种群全局寻优能力,以及避免早熟收敛.利用具有不同特点的测试函数进行验证,结果表明,与同类算法相比,该算法具有较高的精度并兼顾优化解的多样性.
This paper proposes a multi-objective particle swarm optimization (MRBHPSO-SE) algorithm based on stochastic black hole particle swarm optimization algorithm (RBH-PSO) and phase-out strategy.By using the advantages of strong global optimization ability and fast convergence speed of RBH-PSO, the Pareto optimal solution In order to avoid the defect of congestion distance sorting strategy, the strategy of phase-out is proposed and applied to the next-generation particle selection strategy. Meanwhile, the dynamic selection of leading particles and the dynamic inertia weighting coefficient and mutation operation are used to enhance global optimization of population , And to avoid premature convergence.Using the test function with different characteristics to verify the results show that compared with similar algorithms, the algorithm has a high accuracy and take into account the diversity of the optimal solution.