| 改进的粒子群优化算法 |
| |
| 引用本文： | 梁军,程灿. 改进的粒子群优化算法[J]. 计算机工程与设计, 2008, 29(11): 2893-2896 |
| |
| 作者姓名： | 梁军 程灿 |
| |
| 作者单位： | 广西师范大学,计算机科学与信息工程学院,广西,桂林,541004;广西师范大学,计算机科学与信息工程学院,广西,桂林,541004 |
| |
| 摘 要： | 针对基本粒子群优化算法(PSO)易陷入局部极值点,进化后期收敛慢,精度较差等缺点,提出了一种改进的粒子群优化算法.该算法用一种无约束条件的随机变异操作代替速度公式中的惯性部分,并且使邻居最优粒子有条件地对粒子行为产生影响,提高了粒子间的多样性差异,从而改善了算法能力.通过与其它算法的对比实验表明,该算法能够有效地进行全局和局部搜索,在收敛速度和收敛精度上都有显著提高.
|
| 关 键 词： | 粒子群优化 变异 进化计算 函数优化 群智能 |
| 文章编号： | 1000-7024(2008)11-2893-04 |
| 修稿时间： | 2007-06-29 |
Modified particle swarm optimization algorithm |
| |
| LIANG Jun,CHENG Can. Modified particle swarm optimization algorithm[J]. Computer Engineering and Design, 2008, 29(11): 2893-2896 |
| |
| Authors: | LIANG Jun CHENG Can |
| |
| Affiliation: | LIANG Jun,CHENG Can (College of Computer Science , Information Engineering,Guangxi Normal University,Guilin 541004,China) |
| |
| Abstract: | A modified particle swarm optimization algorithm (MPSO) is proposed for improving the disadvantages of basic PSO, as tending to trap into a local optimum, converging slowly in last period of evolution, possibly bringing a consequence in low precision and so on. A random and unconditional mutation strategy which substitutes for previous velocity is presented, and the effect which the best position of neighbor particle has conditionally on the particle behavior is considered. It efficiently increases diversit... |
| |
| Keywords: | particle swarm optimization mutation evolutionary computation function optimization swarm intelligence |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
