基于自适应横向交叉策略的蜜獾算法OA

A honey badger algorithm(HBA)based on adaptive horizontal cross strategy(AHBA)is proposed to address the limitations of the honey badger algorithm when dealing with high-dimensional com-plex problems,such as slow convergence speed,restricted global search ability,and instability.Firstly,a good-point set initialization strategy is introduced to enhance the algorithm's capacity for exploring the diversity within the solution space.Secondly,a novel adaptive horizontal cross strategy is proposed and incorporated into the HBA to improve both the search efficiency and the algorithm's robustness.Final-ly,a guide pooling strategy is adopted to enhance the quality of candidate solutions and reduce the risk of being trapped in local optima.AHBA is compared with five swarm intelligence algorithms on CEC 2022 benchmark functions of varying dimensions,and the effectiveness of different improvement strate-gies is analyzed.The algorithm is also applied to classical engineering problems.Experimental results demonstrate that AHBA exhibits superior optimization performance on high-dimensional problems.