一种基于单纯形搜索的粒子群优化算法

Particle swarm optimization based on simplex search

为了改善粒子群优化算法的求解性能,提出了一种基于单纯形搜索和粒子群优化的混合算法。该算法一方面自适应地确定惯性权重、认知以及社会参数来达到免参数目的,另一方面利用单纯形搜索来引导部分粒子的搜索方向,从而加速算法收敛。数值实验结果表明,与传统的粒子群算法和其他基于单纯形的粒子群算法相比,提出算法在评估次数、求解精度方面表现良好。

In order to improve the performance of particle swarm optimization,this paper proposed a hybrid algorithm based on simplex search and particle swarm optimization.On the one hand,the algorithm adaptively determined the inertia weight,cognition and social parameters for the purpose of avoiding parameters.On the other hand,it used the simplex search to guide the direction of several particles,thus accelerated the convergence of the algorithm.The results of numerical experiments show that the proposed algorithm has better performance than the compared algorithms in terms of function evaluations and accuracy.