| 基于多维度自适应机制改进的混合人工鱼群优化算法 |
投稿时间：2021-09-24 修订日期：2021-09-28  点此下载全文 |
| 引用本文： |
| 摘要点击次数: 152 |
| 全文下载次数: 0 |
|
|
| 中文摘要:传统的人工鱼群算法在优化过程中,前期收敛速度很快,但随着不断的迭代,收敛速度会逐渐下降,很容易出现陷入局部最优无法跳出的情况。鱼群的觅食行为直接影响了算法后期的收敛速度和数值解的精度,而视野与步长则是人工鱼进行觅食行为的基础。前期需要宽广的视野范围与大幅度的步长,后期则要限制视野与步长以提高算法的收敛速度与寻优精度。本文通过自适应视野衰减函数与自适应步长衰减函数来保证寻优解的精度和全局收敛速度,通过权重因子来决定个体鱼的生物行为选择,再利用有向游动机制来提升人工鱼的全局寻优能力,实现了对传统人工鱼群算法的多维度改进。最后设计仿真实验,进行横向对比与纵向对比,验证了本文算法的高效性与优越性。 |
| 中文关键词:人工鱼群算法 自适应视野与步长 过程 权重因子 |
| |
| Hybrid artificial fish swarm optimization algorithm based on multi-dimensional adaptive mechanism |
|
|
| Abstract:The traditional artificial fish swarm algorithm in the optimization process, the early convergence speed is very fast, but with the continuous iteration, the convergence speed will gradually decline, it is easy to fall into the local optimal cannot jump out of the situation. Foraging behavior of fish directly affects the convergence speed and the accuracy of numerical solution in the later stage of the algorithm, and field of vision and step size are the basis of foraging behavior of artificial fish. In the early stage, a wide field of vision and a large step size are needed, and in the later stage, the field of vision and step size are limited to improve the convergence speed and optimization accuracy. Vision based adaptive damping function and adaptive step attenuation function to ensure accuracy and global convergence speed of optimal solution, through weighting factor to determine individual biological behavior choice of fish, reuse Levy to swimming mechanism to improve the global search capability of the artificial fish, realized the multidimensional improvement of traditional artificial fish algorithm. Finally, a simulation experiment is designed to verify the efficiency and superiority of the proposed algorithm. |
| keywords:artificial fish swarm algorithm Adaptive field of vision and step size process Weight factor |
| 查看全文 查看/发表评论 下载pdf阅读器 |
|
|
|
位访问者,今日访问
次