| 一种自适应混合纵向多变异粒子群算法 |
| |
| 引用本文： | 魏媛媛,姚金杰.一种自适应混合纵向多变异粒子群算法[J].东南大学学报(自然科学版),2009(Z2). |
| |
| 作者姓名： | 魏媛媛 姚金杰 |
| |
| 作者单位： | 中北大学信息与通信工程学院; |
| |
| 基金项目： | 山西省研究生优秀创新资助项目(20093079) |
| |
| 摘 要： | 为克服标准粒子群算法搜索后期收敛速度慢、容易陷入局部最优的缺点,通过引进自适应惯性权重因子平衡标准粒子群优化算法的全局搜索和局部改良能力,同时设计了均匀分布变异和高斯分布变异相结合的粒子群混合纵向多变异策略,来提高算法摆脱局部极值和局部寻优的能力.根据提出的改进算法流程,针对公认的Sphere,Rastrigin,Griewank和Salomon四种标准测试函数进行了收敛精度和收敛速度的测试.测试结果表明,在标准粒子群、自适应权重粒子群、自适应变异粒子群和自适应混合多变异粒子群4种算法中,提出的新算法具有最好的全局最优值搜索能力和最稳定的全局收敛特性,且在提高收敛速度的同时,有效地避免了早熟收敛问题.
|
| 关 键 词： | 粒子群算法 惯性权重 自适应变异 混合变异 |
Adaptive particle swarm optimization algorithm with hybrid vertical multi-mutation |
| |
| Wei Yuanyuan Yao Jinjie.Adaptive particle swarm optimization algorithm with hybrid vertical multi-mutation[J].Journal of Southeast University(Natural Science Edition),2009(Z2). |
| |
| Authors: | Wei Yuanyuan Yao Jinjie |
| |
| Affiliation: | Wei Yuanyuan Yao Jinjie (Institute of Information , Communication Engineering,North University of China,Taiyuan 030051,China) |
| |
| Abstract: | To overcome the shortcoming of the standard particle swarm optimization algorithm(PSO),which has low convergence rate and is easy to be trapped in local optimum,the adaptive inertia weight is proposed to balance the global and local search ability,and the hybrid vertical mutation operator combining uniform distribution mutation and Gaussian distribution mutation is developed to improve the abilities to escape from local optima and conduct local search.According to the outline of the proposed algorithm,the c... |
| |
| Keywords: | particle swarm algorithm inertia weight adaptive mutation hybrid mutation |
| 本文献已被 CNKI 等数据库收录！ |
|
