大红斑蝶算法及离子运动算法的改进研究

发布时间：2018-06-14 23:17

本文选题：改进大红斑蝶优化算法(IMBO) + 改进离子运动算法(IIMO)　；参考：《广西民族大学》2017年硕士论文

【摘要】：大红斑蝶优化算法(MBO)和离子运动算法(IMO)均为2015年新提出的群智能随机优化算法。然而这两种算法仍存在局部搜索能力不强、优化精度不高、早熟收敛等不足,算法的理论基础也还不完善。基于这一情况,本论文就如何改进这两种算法的优化性能展开研究。本论文的主要研究成果如下:(1)针对大红斑蝶优化算法仍存在全局搜索能力不强、收敛速度慢、易陷入局部极值之不足,提出一种采用动态分割种群策略的改进MBO算法。该算法采用将群体动态随机分割成两个子群体的策略,不同子群中的大红斑蝶采用不同的搜索方法,以保持种群搜索的多样性。实验结果表明,改进后的MBO算法的全局搜索能力有了明显地提高,在函数优化中具有更好的收敛速度及优化精度。(2)提出一种解决多目标优化问题的MOIMBO。实验结果表明,该算法解决多目标优化问题的平均性能均优于PSO及MBO算法。(3)为了克服离子运动算法(IMO)存在之不足,提出一种新的改进离子运动算法(IIMO)。该IIMO算法基于同类离子相互排斥而异类离子相互吸引、以及离子在液态空间中出现随机移动的特征,刻画出一种新的离子运动数学模型。实验结果表明:IIMO算法比IMO和PSO具有更快的收敛速度、更强的局部搜索能力和全局搜索能力,IIMO算法的鲁棒性比IMO算法和PSO算法强。
[Abstract]:Both MBOs and IMO are new swarm intelligence stochastic optimization algorithms proposed in 2015. However, the two algorithms still have some shortcomings, such as weak local search ability, low optimization accuracy, premature convergence and so on, and the theoretical basis of the algorithm is not perfect. Based on this situation, this paper studies how to improve the optimization performance of these two algorithms. The main research results of this paper are as follows: (1) aiming at the deficiency of global search ability, slow convergence rate and easy to fall into local extremum in the algorithm, an improved MBO algorithm based on dynamic population segmentation strategy is proposed. The algorithm adopts the strategy of randomly dividing the population into two subpopulations, and the different search methods are used by the butterflies in different subgroups to keep the diversity of the population search. The experimental results show that the global search ability of the improved MBO algorithm is obviously improved, and the improved MBO algorithm has better convergence speed and optimization precision in function optimization. The experimental results show that the average performance of the proposed algorithm is better than that of PSO and MBO algorithms. In order to overcome the shortcomings of ion motion algorithm (IMO), a new improved ion motion algorithm (IIMO) is proposed. The IIMO algorithm describes a new mathematical model of ion motion based on the characteristics of the similar ions repel each other and the heterogeneous ions attract each other and the ions move randomly in the liquid space. The experimental results show that the ratio IIMO algorithm has faster convergence speed and stronger local and global search ability than IMO and PSO. The robustness of IIMO algorithm is better than that of IMO algorithm and PSO algorithm.
【学位授予单位】：广西民族大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TP18

【参考文献】