决策空间自组织多模态多目标鲸鱼优化算法研究

针对当前多模态多目标优化算法在获得Pareto解集的完整性、收敛性方面的不足，提出了一种决策空间自组织多模态多目标鲸鱼优化算法(MMO＿SOM＿WOA)。首先将鲸鱼优化算法首次用于求解多模态多目标问题，通过鲸鱼优化算法本身的随机性提高寻找Pareto解集完整性的能力。其次将自组织映射网络与鲸鱼优化算法相结合，迭代开始时为鲸鱼优化算法建立良好的邻域。最后使用精英反向学习策略初始化种群和非支配排序机制获得均匀且完整的解。通过与当前5种经典算法在多模态多目标优化问题上进行仿真对比，结果表明MMO＿SOM＿WOA算法兼顾Pareto解集的多样性和Pareto解的完整性，收敛速度和收敛精度均得到提升具有较高的性能，有效解决多模态多目标优化问题。

Research on self-organizing multi-modal multi-objective whale optimization algorithm in decision space

Aiming at the deficiency of current multi-mode multi-objective optimization algorithm in obtaining the integrity and convergence of Pareto solution set, a decision space self-organizing multi-mode multi-objective whale optimization algorithm (MMO_SOM_WOA) is proposed. First, whale optimization algorithm is used to solve multi-modal multi-objective problems for the first time, and the ability to find the integrity of Pareto solution set is improved through the randomness of whale optimization algorithm itself. Secondly, the self-organizing mapping network is combined with whale optimization algorithm to establish a good neighborhood for whale optimization algorithm at the beginning of iteration. Finally, the elite reverse learning strategy is used to initialize the population and non dominated sorting mechanism to obtain uniform and complete solutions. Through simulation comparison with the current five classical algorithms on multi-modal multi-objective optimization problems, the results show that MMO_SOM_WOA algorithm takes into account both the diversity of Pareto solution set and the integrity of Pareto solution. The convergence speed and convergence accuracy are improved and have high performance, effectively solving multi-modal and multi-objective optimization problems.