具有Levy变异和精英自适应竞争机制的蚁狮优化算法

PDF下载HTML

Title:

Ant lion optimizer with levy variation and adaptive elite competition mechanism

作者:

景坤雷^1,2, 赵小国^1,2,3, 张新雨^1,2, 刘丁^1,2

1. 西安理工大学 晶体生长设备及系统集成国家地方联合工程研究中心, 陕西 西安 710048;
2. 陕西省复杂系统控制与智能信息处理重点实验室, 陕西 西安 710048;
3. 西安建筑科技大学 机电工程学院, 陕西 西安 710055

Author(s):

JING Kunlei^1,2, ZHAO Xiaoguo^1,2,3, ZHANG Xinyu^1,2, LIU Ding^1,2

1. National & Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration, Xi’an University of Technology, Xi’an 710048, China;
2. Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing, X

关键词:

蚁狮优化算法; Levy变异; 精英自适应竞争; 收敛速度; 硅单晶; 参数辨识

Keywords:

ant lion optimizer; Levy variation; adaptive elite competition; convergence speed; parameters identification

分类号:

TP18

DOI:

10.11992/tis.201706091

摘要:

针对蚁狮优化算法易陷入局部最优、收敛速度慢的缺点，本文提出一种具有Levy变异和精英自适应竞争机制的蚁狮优化算法。利用服从Levy分布的随机数对种群较差个体进行变异，可改善种群多样性提高算法的全局搜索能力；精英自适应竞争机制使得多个精英并行带领种群寻优，提高了算法的收敛速度，为避免较大计算量，并行竞争的精英个数会随着寻优代数增加而减少。同多个改进算法进行比较，结果表明本文所提算法具有更好的寻优精度和收敛速度。最后将本文改进算法应用于硅单晶热场温度模型的参数辨识，仿真结果说明该算法具有较好的参数辨识能力。

Abstract:

The ant lion optimizer (ALO) reveals such deficiencies as easily relapsing into local optimum and low convergence speed. This paper proposed an improved ALO algorithm with Levy variation and adaptive elite competition mechanism. By carrying out Levy variation to poor individuals, the diversity of population and the global search ability of the algorithm can be increased. Moreover, the adaptive elite competition mechanism that many elites lead the population to search at the same time can improve the convergence speed of the algorithm. To reduce the amount of calculation, the number of the elites competing in parallel will decrease with the increase of iterations. By contrast with other improved optimization algorithms, the test results show that the improved algorithm proposed in this paper has better search precision and convergence speed. Finally, this improved algorithm is applied to identify parameters of silicon single crystal thermal field temperature model and the simulation results prove its excellent ability of parameters identification.