基于直觉模糊种群熵的自适应粒子群算法

Adaptive particle swarm optimization algorithm based on intuitionistic fuzzy population entropy

基本粒子群算法在求解高维空间的复杂多峰函数时,种群多样性丧失很快,从而导致算法早熟收敛。针对这一问题,提出了将直觉模糊种群熵作为运算过程中种群多样性的测度,并将直觉模糊熵作为参数来影响粒子的速度更新机制,减小了算法在运算后期早熟收敛的概率,并使算法具备了一定的自适应性。实验结果表明,改进后的算法在性能上比基本粒子群算法有了较大的改进。

For complex multi-peaks function with high dimensions, canonical Particle Swarm Optimization Algorithm （PSOA） has big chance falling in premature convergence for the fast losing of population diversity. With the disadvantages, the intuitionistic fuzzy population entropy was presented as the estimate of the diversity of the population in this paper. By applying the intuitionistic fuzzy population entropy as parameter in velocity updated mechanism, the improved PSOA can prevent premature convergence, which can also provide the PSOA with adaptabily. The experiments show the Improved PSOA is significantly superior to canonical PSOA.