摘要
针对灰狼优化算法在求解连续函数优化问题时精度不高、易出现早熟收敛等缺陷,提出一种改进的灰狼优化算法.该算法在初始种群个体时采用混沌序列方法,为算法全局搜索的多样性奠定基础.根据个体适应度值将种群分为两个子种群,分别执行不同的搜索方式,以平衡算法的开采能力和勘探能力.选取几个标准测试函数对算法性能进行测试,测试结果表明,与其他群智能优化算法相比,该算法在求解精度和收敛速度方面均具有较强的竞争力.
Aimed at the defect of grey wolf optimization（GWO）algorithm for solving the problem of continuous function optimization such as low precision and easy to fall in premature convergence,an improved GWO algorithm is proposed.In this algorithm,chaotic sequence method is used onto the initiale individual of the population,laying a basis of diversity of global searching for the algorithm.The population is divided into two sub-populations based on the fitness of the individual and different searching modes are executed,respectively to balance the exploration ability and the exploitation ability of the algorithm.The performance of proposed algorithm is then tested with a couple of standard test functions.It is shown by the measurement result that compared with other swarm intelligence standard GWO algorithms,the proposed algorithm possesses a stronger competitive capability in connection with the accuracy of solution and its convergence speed.
出处
《兰州理工大学学报》
CAS
北大核心
2016年第3期96-101,共6页
Journal of Lanzhou University of Technology
基金
贵州省科学技术基金(黔科合J字[2007]2204号)
关键词
灰狼优化算法
函数优化
群智能
混沌
grey wolf optimization algorithm
function optimization
swarm intelligence
chaos
