计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (26): 35-38.

• 研究、探讨 • 上一篇    下一篇

一种结合混沌和逃逸的自适应粒子群优化方法

冯昌利,高雷阜   

  1. 辽宁工程技术大学 数学与系统科学研究所,辽宁 阜新 123000
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-09-11 发布日期:2011-09-11

Improved adaptive particle swarm optimization method based on self-adaptive escape and chaos

FENG Changli,GAO Leifu   

  1. Institute of Mathematics and Systems Science,Liaoning Technical University,Fuxin,Liaoning 123000,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-09-11 Published:2011-09-11

摘要: 考虑到粒子群早熟收敛现象,提出了一种基于逃逸和混沌的自适应粒子群优化算法。该算法引入一个新的惯性系数来改进原有的速度更新公式,并在粒子陷入早熟之后,调整相应的速度参数。同时,选取适应度最差的10%的粒子,利用混沌的方法对它们的位置进行更新,并且格栅化。产生了充分多的点,使粒子群跳出了当前的局部最优并获得更优的群体最优值。数值仿真表明,该算法粒子群能有效地跳出局部极值,获得精度更高的优化值。

关键词: 粒子群, 早熟, 自适应, 逃逸, 混沌

Abstract: To solve the premature convergence problem of the Particle Swarm Optimization(PSO),an improved PSO method based on self-adaptive escape velocity and chaos is proposed.A new inertial parameter is introduced to amend the original velocity equation.When the particle arrived at local best solution,the algorithm has modified the correspondent velocity parameters.Meanwhile,the particles whose fitness is listed 10% worse are modified by the use of chaos methods and are grided,by which more points are created to get a better global best solution.Simulation results show that this algorithm can escape from local optima and achieve more accurate solutions.

Key words: Particle Swarm Optimization(PSO), premature convergence, self-adaptive, escape, chaos