摘要
针对人工蜂群算法探索能力强但开发能力弱等特性,提出一种均衡蜂群算法。该算法根据"适应值欧式距离比"策略和差分算法改进更新公式,"适应值欧式距离比"策略有助于多峰问题的优化,而差分算法善于优化单峰问题,为发挥两者的优势,提出了一种新的搜索结构,有利于探索与开发能力达到平衡。在初始化时引入混沌策略提高种群多样性。在连续域内,12个标准测试函数的仿真结果表明,本算法能有效地提高最优解的精度,加快收敛速度。在离散域内,采用4个标准柔性作业车间调度模型,验证了本算法在解决实际问题中的可行性和优越性。
According to the power exploration and poor exploitation ability of artificial bee colony(ABC), a balanced bee colony(FER-ABC) was proposed. This algorithm modified the search equation based on 'fitness Euclidean-distance ratio' and differential algorithm(DE). The FER strategy is useful for multi-optimization and the DE is beneficial to single- optimization. In order to exploit the advantages to full, a new search structure was proposed which balanced the exploitation and exploration. For continuous problems, the simulations on twelve benchmark functions indicate that this FER-ABC algorithm can improve the accuracy effectively and increase the convergence rate apparently. For the discrete problem, this proposed algorithm is proved to be feasible and advantageous on the simulation of four standard flexible job shop scheduling module.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2015年第5期980-989,共10页
Journal of System Simulation
基金
国家高技术研究发展计划课题(2013AA04 0405)
关键词
人工蜂群算法
均衡蜂群算法
混沌策略
“适应值欧式距离比”策略
差分算法
artificial bee colony
balanced bee colony
chaotic strategy
'fitness Euclidean-distance ratio' strategy
differential algorithm