To address the defects of the traditional egret swarm optimization algorithm (ESOA) in high-dimensional complex optimization problems, such as low optimization accuracy, weak ability to escape from local extrema, rapid decay of population diversity, and insufficient efficiency in the late convergence stage, an improved egret swarm optimization algorithm (IESOA) combining variable-factor weighted learning and adjacent generation dimension crossover strategy is proposed. Firstly, a dynamic change rule of core model parameters (exploration factor ω and exploitation factor μ) is constructed to adaptively adjust with the iteration process, so as to balance global exploration and local exploitation capabilities. Secondly, a multi-individual variable-factor weighted learning mechanism is designed to enable offspring individuals to inherit the position information of following individuals, sub-population optimal individuals, and global optimal individuals simultaneously, avoiding excessively fast assimilation of the population. Furthermore, an adjacent generation dimension crossover strategy is established to update the optimal individual based on the priority principle of absolute dimension difference, fully retaining the historical optimal dimension information. Finally, a preferred mutation reverse learning strategy is integrated to further enhance the local extremum escape ability and convergence accuracy of the algorithm. The IESOA is compared with eight algorithms, including PSO, DE, SBOA, BKA, HHO, DOA, and the original ESOA on CEC2014 and CEC2019 benchmark test suites. The results show that IESOA presents significant advantages in optimization accuracy, convergence speed, and stability. The algorithm is applied to three typical engineering optimization problems: reinforced concrete beam design, welded beam design, and pressure vessel design, which effectively reduces the structural design cost and verifies its application value in practical engineering.
Wang et al. (Sat,) studied this question.