双曲正切高斯与两阶段反向学习平衡优化算法

Hyperbolic Tangent Gaussian and Two-stage Opposition-based Learning Equilibrium Optimizer Algorithm

针对平衡优化算法易陷入局部最优以及收敛速度慢等缺点,提出双曲正切高斯与两阶段反向学习平衡优化算法.首先,将双曲正切函数与黄金分割系数融入高斯分布动态调整算法的全局搜索能力,提高算法寻优精度;其次,为了缓解迭代中种群多样性减少,对种群个体执行遗传算法中交叉和变异操作,使种群最大程度上避免多样性减少;然后,通过两阶段反向学习,种群个体能够通过一般反向学习或随机反向学习增强算法逃离局部最优的能力和加快算法收敛的速度;最后,使用12个基准测试函数、CEC2014函数集、Wilcoxon秩和检验及Friedman秩检验测试改进算法的综合性能,并与其他改进群智能算法进行对比,实验结果表明改进算法优势明显.

Aiming at the disadvantages of equilibrium optimizer algorithm,such as falling into local optimum and slow convergence rate,a hyperbolic tangent Gaussian and two-stage opposition-based learning equilibrium optimizer algorithmis proposed.Firstly,the hyperbolic tangent function and golden section coefficient are integrated into the global search ability of the Gaussian distribution dynamic adjustment algorithm to improve the optimization accuracy of the algorithm.Secondly,in order to alleviate the decrease of population diversity during iteration,the crossover and variation operations of genetic algorithm were performed on the individuals of the population to avoid the decrease of population diversity to the greatest extent.Then,through two-stage reverse learning,the individual population can enhance the ability of the algorithm to escape from the local optimal and speed up the convergence of the algorithm through general reverse learning or random reverse learning.Finally,12 benchmark functions,CEC2014 function set,Wilcoxon rank sum test and Friedman rank test were used to test the comprehensive performance of the improved algorithm,and compared with other improved swarm intelligence algorithms,the experimental results show that the improved algorithm has obvious advantages.