为了平衡种群规模对算法搜索效率和有效性的影响,提出了一种种群规模可变的免疫克隆算法求解多模态函数优化问题。给出了种群规模的变化规则、变化幅度和变化的具体实现过程,实现了种群规模根据进化过程自适应的动态变化。此外,结合多模态函数优化的特点,采用Baldwin学习作为局部搜索机制,增强算法搜索最优解的能力。实验结果表明,本算法寻优能力较强,收敛速度较快,并且较为稳定。 In order to balance the effect of population size on the search efficiency and validity of the algorithm, a variable population immune clonal algorithm is proposed to solve the multi-modal function optimization problem. The specific implementation of the rule of population variation, the variation range and the change of population size are given, and the dynamic change of population size adaptively according to the evolutionary process is achieved. In addition, combined with the characteristics of multi-modal function optimization, Baldwin learning is used as a local search mechanism to enhance the ability of the algorithm to search for the optimal solution. The experimental results show that the algorithm has better ability of searching for optimal solutions and faster convergence rate, and is more stable.