基于混沌知识迁移的多种群粒子群文化算法-控制理论与应用.PDF

28 9 Vol. 28 No. 9 2011 9 Control Theory Applications Sep. 2011 :2011 , , , (, 221116) : , . , , . , ; , , . , , . : ; ; ; : TP301 : A Multi-population particle swarm cultural algorithms adopting chaotic knowledge migration GUO Yi-nan, CHENG Jian, CAO Yuan-yuan, LIU Dan-dan (College of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou Jiangsu 221116, China) Abstract: In existing multi-population particle swarm cultural algorithms based on knowledge migration, the migrated knowledge may not reflect the best individuals in the advantageous region. In order to improve the efficiency of knowledge migration, a novel multi-population particle swarm cultural algorithms adopting chaotic knowledge migration is proposed. Chaos sequence is used to deeply explore migrated cells for improving the validity of migrated knowledge. Knowledge migration interval is then dynamically adjusted by generation. This keeps the diversity of population in the early evolution and accelerates the convergence in the latter evolution. Simulation results indicate that the algorithm effectively improves the speed of convergence and eliminates premature convergence. Key words: chaos sequence; knowledge migration; multi-population; particle swarm cultural algorithms 1 (Introduction) , . , . . , , , , , . , . Coelho (multi-population particle swarm cultural algo- rithms adopting chaotic knowledge migration, MPSC- , , , , CKM). .