###
DOI:
本文二维码信息
引入迁移和变异策略的改进鸟群算法及其在参数估计中的应用
王建伟
(华东理工大学)
Improved bird swarm algorithm based on migration and mutation strategy and its application in parameter estimation
wangjianwei
(East China University of Science and Technology)
摘要
相似文献
本文已被:浏览 219次   下载 22
投稿时间:2017-07-09    修订日期:2017-08-14
中文摘要: 为了解决鸟群算法(BSA)易陷入局部最优问题,提出了一种引入迁移策略和变异策略的改进鸟群算法(IBSA)。在鸟群飞行阶段引入迁移策略有助于提高鸟群向适应度更高位置迁移能力,提高鸟群算法的收敛速度;在寻优后期引入变异策略,提高鸟群的局部寻优能力,提高了算法的寻优能力。选取6个典型的测试函数进行寻优实验,实验证明与PSO、BA、BSA算法相比,IBSA具有更高的寻优精度和更快的寻优速度。在此基础上,将IBSA应用于发酵动力学模型参数估计中,与Gauss-Newton、GA、MAEA等算法相比,IBSA的参数估计值的偏差平方和最小,具有更高的模型拟合精度。
Abstract:In order to solve the shortcoming of the local optima for bird swarm algorithm,an improved bird swarm algorithm (IBSA) is proposed, which introduces migration strategy and mutation strategy. Introducing the migration strategy into the stage of flight is helpful to improve the birds to adapt to a higher degree of migration ability and to improve the convergence speed of BSA; In the later stage of the optimization, introducing the mutation strategy is helpful to improve the local searching ability of the bird swarm and to improve the searching ability of the algorithm. 6 typical test functions are selected to perform the optimization experiment and the result of experiment show that IBSA has higher searching precision and faster searching speed compared with PSO、BA and BSA. Finally, IBSA is used to estimate the parameters of the fermentation kinetic model. Compared with Gauss-Newton, GA, MAEA, the parameters estimated by IBSA have the least square Sum of Deviations Squares and IBSA has Higher model fitting accuracy.
文章编号:20170709001     中图分类号:    文献标志码:
基金项目:
引用本文:
王建伟.引入迁移和变异策略的改进鸟群算法及其在参数估计中的应用[J].华东理工大学学报(自然科学版),DOI:.

用微信扫一扫

用微信扫一扫