多策略改进的天鹰优化算法及其应用

Multi-strategy improved aquila optimizer and its application

为改善天鹰优化算法(aquila optimizer, AO)在求解复杂优化问题时存在易陷入局部最优等不足,提出一种多策略改进的天鹰优化算法(multi-strategy improved aquila optimizer, MIAO)。首先,提出镜像单纯形法策略扩大天鹰搜索范围,提升种群多样性和逃离桎梏能力;其次,在天鹰算法的X3阶段融入社会自由觅食策略,摆脱全局平均值的束缚,提升迭代后期天鹰个体的多样性;同时,将阶梯步进策略引入X4阶段,保证当前优势个体加快向全局最优前进的趋势,增加收敛速度;最后,改进原有开发机制,提升算法寻优能力。对10个常用基准函数以及CEC2017部分函数进行寻优实验,实验结果与Wilcoxon符号秩和检验结果均表明改进算法具有更好的寻优精度、收敛性能和稳定性。另外,通过一个机械优化设计实验进行测试分析,进一步验证所改进算法的优越性和实用性。

In order to improve the shortcomings of the aquila optimizer(AO)in solving complex optimization problems,such as easily falling into local optimality,this paper proposed a multi-strategy improved aquila optimizer(MIAO).Firstly,this paper proposed the mirror simplex method strategy to expand the search range of aquila optimizer,enhancing the population diversity and the ability to escape from shackles.Secondly,the X3 phase of the aquila optimizer combined the social free foraging strategy to escape from the bondage of global mean and improved the diversity of individual aquatic eagles in the late iteration.At the same time,the X4 phase incorporated the ladder stepping strategy to ensure that the current dominant individuals accelerated the trend toward the global optimum and increased the convergence speed.Finally,it enhanced the optimization ability of the algorithm by improving the original development mechanism.Experimental results and Wilcoxon signed rank sum test results of 10 commonly used benchmark functions and some of the CEC2017 functions show that the improved algorithm has better performance in terms of accuracy,convergence and stability.In addition,through testing and analyzing a mechanical optimization design experiment to further verify the superiority and practicability of the improved algorithm.