基于反向学习的自适应α约束病毒种群搜索算法
发布时间：2018-08-22 13:36
【摘要】：为了提高该算法求解约束优化问题的能力,提出一种新的约束病毒种群搜索算法。首先,提出自适应α-level比较策略,以在算法的不同阶段充分利用可行个体与不可行个体的有效信息;其次,为了进一步提高算法求解约束优化问题的收敛速度和搜索精度,针对算法的病毒扩散行为,提出了结合反向学习机制的搜索方程,以提高种群多样性并加速全局收敛。对CEC2006中13个约束优化函数的对比仿真结果表明,本文算法在搜索精度、收敛速度以及稳定性方面,相比于αSimplex算法、粒子群遗传算法算法、交叉人工蜂群算法算法以及约束改进差分进化算法算法具有明显优势。同时将该算法应用于无人机协同实时航迹规划约束优化问题中,通过仿真实验并与利用约束改进差分进化算法对这一问题进行求解的方法进行对比,验证了本文算法在规划效率、规避威胁等方面的优越性。
[Abstract]:In order to improve the ability of the algorithm to solve constrained optimization problems, a new constrained virus population search algorithm is proposed. Firstly, an adaptive 伪 -level comparison strategy is proposed to make full use of the effective information between feasible and infeasible individuals at different stages of the algorithm. Secondly, in order to further improve the convergence speed and search accuracy of the algorithm for solving constrained optimization problems, In order to improve population diversity and accelerate global convergence, a search equation based on reverse learning mechanism is proposed for the virus diffusion behavior of the algorithm. The simulation results of 13 constrained optimization functions in CEC2006 show that, compared with 伪 Simplex algorithm, the PSO algorithm in this paper is more accurate, faster and more stable than the 伪 Simplex algorithm. Crossover artificial bee colony algorithm and constrained improved differential evolution algorithm have obvious advantages. At the same time, the algorithm is applied to the constrained optimization problem of UAV collaborative real-time track planning. The simulation results are compared with the method of using constrained improved differential evolution algorithm to solve the problem. The superiority of this algorithm in planning efficiency and avoiding threat is verified.
【作者单位】： 空军工程大学航空航天工程学院;复杂航空系统仿真重点实验室;95994部队;
【基金】：国家杰出青年科学基金资助项目(71501184)
【分类号】：TP18
[Abstract]:In order to improve the ability of the algorithm to solve constrained optimization problems, a new constrained virus population search algorithm is proposed. Firstly, an adaptive 伪 -level comparison strategy is proposed to make full use of the effective information between feasible and infeasible individuals at different stages of the algorithm. Secondly, in order to further improve the convergence speed and search accuracy of the algorithm for solving constrained optimization problems, In order to improve population diversity and accelerate global convergence, a search equation based on reverse learning mechanism is proposed for the virus diffusion behavior of the algorithm. The simulation results of 13 constrained optimization functions in CEC2006 show that, compared with 伪 Simplex algorithm, the PSO algorithm in this paper is more accurate, faster and more stable than the 伪 Simplex algorithm. Crossover artificial bee colony algorithm and constrained improved differential evolution algorithm have obvious advantages. At the same time, the algorithm is applied to the constrained optimization problem of UAV collaborative real-time track planning. The simulation results are compared with the method of using constrained improved differential evolution algorithm to solve the problem. The superiority of this algorithm in planning efficiency and avoiding threat is verified.
【作者单位】： 空军工程大学航空航天工程学院;复杂航空系统仿真重点实验室;95994部队;
【基金】：国家杰出青年科学基金资助项目(71501184)
【分类号】：TP18
【相似文献】
相关期刊论文 前10条
1 许中卫;李炜;宋杰;吴建国;;束搜索算法的精度优化研究[J];计算机工程与应用;2006年09期
2 黄帅;马良;;一种改进的和声搜索算法[J];小型微型计算机系统;2012年11期
3 ，
本文编号：2197257
本文链接：https://www.wllwen.com/kejilunwen/zidonghuakongzhilunwen/2197257.html
