双种群协同演化的改进蜜獾算法

Improved honey badger algorithm for dual population collaborative evolution

针对蜜獾算法存在的局部搜索能力不足、易陷入局部最优值等问题,提出一种双种群协同演化的改进蜜獾算法。在初始化阶段采用Cubic混沌映射对种群进行初始化,扩大可行解的搜索范围并提高种群的分布均衡性;引入融合黏菌算法和蜜獾算法的双种群优化机制,依托两者的更新优势协同推进个体逼近目标位置,进而提高整个算法的搜索效率和优化性能;采用柯西随机反向扰动策略对蜜獾种群最优位置进行扰动,以提高算法跳出局部最优的能力。通过评估单一策略的改进有效性实验、与七种对比算法的不同高维实验以及Wilcoxon秩和检验,结果表明该算法具有良好的收敛精度和求解速度。最后将改进算法应用于压缩弹簧设计和压力容器设计问题,进一步验证了改进策略的有效性及该算法的工程实用性。

To address the weaknesses of the honey badger algorithm,specifically its limited capacity for local search and susceptibility to local optima,this paper proposed an enhanced version based on coevolution with two populations.This approach used Cubic chaotic mapping to initialize the population,thereby expanding the search space and improving its distribution.Moreover,it introduced a dual-population optimization mechanism that combined the slime mold algorithm with the honey ba-dger algorithm.By leveraging the strengths of both methods,the individuals could more effectively hone-in on the target location,resulting in improved search efficiency and optimization performance.To further improve the algorithm’s ability to escape local optima,it employed a Cauchy random reverse perturbation strategy to disturb the optimal position of the honey badger population.By means of the experiment of improving the effectiveness of a single strategy,different high-dimensional experiments with seven other algorithms and Wilcoxon rank-sum tests,experimental results demonstrate that the proposed algorithm has high convergence accuracy and fast solving times.Finally,this paper applied the improved algorithm to the design of compression springs and pressure vessels,which further confirmed the efficacy of improved strategy and the practical utility of the algorithm.