粒子群遗传融合算法

提出一种融合粒子群算法和遗传算法改进优化算法,该算法首先采用一种自适应弹性粒子群算法,弹性地修正粒子速度的幅值,有效地避免了粒子群算法的早熟收敛问题。再与遗传算法融合,模仿自然界的个体成熟过程,对遗传算法中的每一代群体中的优秀个体,先采用自适应弹性粒子群算法获得进一步的提高。再经过提高、交叉、变异三步,获得最优解。以动态系统FCRNN的设计为例,改进算法收敛速度快,误差精度高。

A Fusion Algorithm of Particle Swarm Algorithm and Genetic Algorithm

A improved algorithm(GARPSO) is presented which merges the particle swarm algorithm and genetic algorithm. Firstly in the new algorithm, an adaptive resilient particle swarm algorithm(RPSO) is adopted to adjust the magnitude of the velocity resiliently and avoid premature convergence effectively. Secondly, combining with genetic algorithm, mimicing the mature process in nature, Optimal individuals of every generation in genetic algorithm get the further improvement by RPSO algorithm. Through three steps of improvement, crossover, mutation, the GARPSO algorithm can get the optimum solution. Through the dynamic system FCRNN design , convergence rate and error precision of the improved algorithm get perfect effect.