基于混沌和差分进化的混合粒子群优化算法

Hybrid Particle Swarm Optimization Algorithm Based on Chaos and Differential Evolution

研究粒子群算法优化问题,由于标准粒子群优化算法(PSO)在高维复杂函数优化中易早收敛,影响全系统优化。为改进的混合粒子群优化算法,提出了一种基于混沌和差分进化的混合粒子群优化算法(CDEHPSO)。把基于Logistic映射的混沌序列引入到种群初始化操作中。在算法进化过程中,通过一种粒子早熟判断机制,在基本粒子群优化算法中引入了差分变异、交叉和选择操作,对早熟粒子个体进行差分进化操作,从而维持了种群的多样性并有效避免了算法陷入局部最优。仿真结果表明,相比于粒子群优化算法和差分进化算法(DE),CDEHPSO算法具有收敛速度快、搜索能力强的优点。

An improved particle swarm optimization algorithm was studied in this paper and a hybrid particle swarm optimization algorithm was proposed based on chaos and differential evolution （CDEHPSO） to solve the premature convergence of standard particle swarm optimization algorithm （PSO） when applied to high - dimensional complex function optimization problems. Firstly, the initial population was generated by the chaos sequence based on Logistic map. In the evolutionary process of the proposed algorithm, in order to maintain the diversity of the population and avoid falling into the local optimum the differential mutation, crossover and selection operations were involved into PSO algorithm of the premature particles based on a premature judgment mechanism. The results show the improvement of the CDEHPSO algorithm in the convergence speed and searching ability compared with PSO and DE algorithm.