入侵杂草算法的一种改进实现  

An Improved Implementation of Invasive Weed Algorithm

作　　者：陈林[1] 潘大志[1] 

机构地区：[1]西华师范大学数学与信息学院,四川南充637009

出　　处：《西华师范大学学报（自然科学版）》2017年第3期304-309,共6页Journal of China West Normal University(Natural Sciences)

基　　金：四川省教育厅自然科学基金(14ZA0127);西华师范大学博士启动基金(12B022);西华师范大学校级科研团队(CXTD2015-4);2016年西华师范大学大学生创新创业项目(CXCY2016005)

摘　　要：针对入侵杂草算法寻优精度不高、收敛速度慢和易早熟等缺陷,提出一种改进的入侵杂草算法。新算法将每个杂草的所有种子作为一个小生境,先对每个小生境进行学习算子操作,再引用复合形法引导种群进行协同寻优,最后对种群进行有向的扰动操作,从而得出最优解。实验测试表明,新算法在寻优效率、解的稳定性和鲁棒性等方面都较好。Aiming at the defects of low precision,slow convergence rate and easy early maturity of the invasive weed algorithm,an improved algorithm is proposed. The new algorithm will first of all take each weed as a niche,and learning operator of each niche is presented. Then,the complex method is introduced to guide the population of collaborative optimization. Finally,the disturbance to the operation of the population is conducted to obtain the optimal solution. Experimental results show that the new algorithm is better in the aspects of optimization efficiency,stability and robustness of the solution.

关 键 词：小生境 学习算子 复合形法 扰动 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]