欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为提高教与学优化算法的综合性能,提出一种基于混合策略的自适应教与学优化算法.将随机性学习与有向性学习融合,提出一种自适应综合交叉学习策略,根据进化的不同阶段自适应地选择学习方式,增强算法对解的搜索能力;加入一种方向性的扰动策略,增大种群多样性,较大程度地加大了对搜索空间的探索力度,降低了种群陷入局部最优的可能.基于标准测试函数的仿真实验结果表明,本文算法可有效避免算法陷入局部最优,在收敛精度和收敛速度上有较大提高.
英文摘要：
In order to improve the overall performance of teaching?and?learning?based optimization ( TLBO) , in this paper , we propose a new self?adaptive teaching?and?learning?based optimization algorithm that uses a mixed strategy ( MSTLBO) . This strategy combines adaptive integrated cross learning with random and directional learning. These learning methods are chosen adaptively to enhance the searching ability for different evolutionary stages. We adopt a kind of directional disturbance strategy to increase the population diversity, and to avoid the possibility of the popu?lation falling into a local optimum. The experimental results on the benchmark functions show that the MSTLBO ex?hibits good performance in avoiding premature convergence, and both the convergence accuracy and convergence rate are significantly improved.
同期刊论文项目
同项目期刊论文
期刊信息
位置：