摘要
粒子群算法(particle swarm optimization,PSO)是一种容易实现且高效的优化算法,但该算法对各种参数反应较为敏感.本文针对经典粒子群算法容易陷入局部最优的不足之处进行研究,提出对经典粒子群算法使用自适应惯性权重并引入模拟退火法的思想来解决经典粒子群优化算法容易陷入局部最优解的问题.仿真实验结果表明,本文提出的混合算法与经典粒子群算法相比,不仅能够避免寻优过程中陷入局部最优问题,而且还具有收敛速度快、成功次数高、稳定性及寻优结果好等特点.
Particle swarm optimization algorithm is an optimization algorithm which is efficient and easy to implement, but the algorithm is more sensitive with various parameters. In this paper, we research the classical particle swarm optimization algorithm in the view of its shortcomings that is easy to fall into local optimum, and then puts forward the idea of using adaptive inertia weights and introducing the simulated annealing method to classical particle swarm optimization algorithms to solve the problem that local optimal solution of classical particle swarm optimization algorithm. Compared with the classical algorithm, the simulation results show that the proposed hybrid algorithm can not only avoid the local optimal solution in the process of particle swarm optimization but also has the characteristics of fast convergenee, high success times, stability and good results.
出处
《哈尔滨理工大学学报》
CAS
北大核心
2016年第3期49-53,共5页
Journal of Harbin University of Science and Technology
基金
国家自然科学基金(61172149
61402132)
关键词
自适应
惯性权重
模拟退火法
粒子群优化
混合算法
self-adaptation
inertia weight
simulated annealing
particle swarm optimization
hybrid algorithm
