基于调节算子的多目标人工蜂群算法 |
A Multi-Objective Artificial Bee Colony Algorithm based on Regulation Operators |
摘要点击 287 全文点击 0 投稿时间:2019-04-26 修订日期:2020-01-03 |
查看/发表评论 下载PDF阅读器 |
中文关键词 人工蜂群算法 多目标优化 调节算子 外部档案 多样性个体 |
英文关键词 artificial bee colony multi-objective optimization regulation operators external archive diversity individuals |
基金项目 河北省自然科学基金 |
作者 | 单位 | 邮编 | 赵新秋 | 燕山大学 | 066004 | 段思雨 | 燕山大学 | 066004 | 马学敏 | 燕山大学 | |
|
中文摘要 |
针对人工蜂群算法处理复杂优化问题在进化后期收敛速度较慢、精度低、易陷入局部最优等问题, 提出了一 种基于调节算子的人工蜂群算法. 首先, 在进化过程中考虑蜜源开发情况, 并根据蜜源情况自适应地选择搜索半径, 在各个时期侧重于不同搜索方向. 其次, 将分布情况纳入适应度值计算中, 利用轮盘赌策略选择种群中多样性解引 导种群进化. 最后, 通过将外部档案个体维度混合, 保证良好的分布性, 并在多组测试函数下验证了算法的有效性. |
英文摘要 |
The arti?cial bee colony algorithm has many defects, such as slow convergence speed, low convergence precision and easily to fall into local minima in the late stage of evolution. In order to overcome those shortcoming, we proposed a Regulation operators-based multi-objective arti?cial bee colony algorithm. Firstly, the search radius is adaptively selected according to exploitation ability of honey, and focused on different search directions in different periods. Secondly, the ?tness values of individuals are calculated in terms of distribution. Then the diversity solutions is selected by roulette wheel selection strategy to guide evolution. Finally, merging the individual dimensions of the external archives to ensure distribution, the results of test functions demonstrate the validity of the algorithm. |
关闭 |
|
|
|
|
|