哈尔滨工程大学学报2011，Vol.32Issue(12)：1617-1623,7.DOI:10.3969/j.issn.1006-7043.2011.12.016
双尺度协同变异的离散粒子群算法
Discrete particle swarm optimization based on double-scale cooperation mutation
摘要
Abstract
To deal with the problem in discrete particle swarm optimization of the particles searching blindly and not being able to carry out a deep local search around the current optimal solution, a discrete particle swarm optimization ( DPSO) algorithm based on double-scale cooperation velocity mutation was proposed. The double-scale velocity mutation operator was introduced for the current optimal solution, which can not only improve the local search function, but also increase the precision of the optima solution. The coarse-scale mutation operator can be utilized to quickly localize the global optimized space at early evolution. The novel scale-changing strategy produced a smaller fine-scale mutation operator according to the evolution and developed mutation operators with fine-scale possibilities to implement a local accurate minima solution search at the late evolution stage. The experimental studies on five standard benchmark functions and the experimental results show that the proposed method can not only effectively solve the problem of a lack of local search ability, but also significantly speed up the convergence while improving the stability.关键词
离散粒子群/双尺度/协同变异Key words
discrete particle swarm optimization/ double-scale/ cooperative mutation分类
信息技术与安全科学引用本文复制引用
陶新民,王妍,赵春晖,刘玉..双尺度协同变异的离散粒子群算法[J].哈尔滨工程大学学报,2011,32(12):1617-1623,7.基金项目
国家自然科学基金面上资助项目(61074076) （61074076）
中国博士后科学基金资助项目(20090450119) （20090450119）
中国博士点新教师基金资助项目(20092304120017) （20092304120017）
