基于阶段自适应与差分进化的中华穿山甲优化算法

Chinese Pangolin Optimizer Algorithm Based on Stage Adaptation and Differential Evolution

摘要: 针对原始中华穿山甲优化算法在中后期收敛速度慢、局部开发能力不足和求解精度不高等问题，本文提出一种融合阶段自适应搜索、差分进化增强与局部精修机制的改进中华穿山甲优化算法。该算法通过混沌对立初始化提高初始种群质量，通过阶段自适应机制协调前期探索与后期开发，并在中后期引入差分进化增强与局部精修策略以提高收敛速度和求解精度。本文采用平均值、标准差和Wilcoxon秩和检验进行定量分析。结果表明，改进算法在整体性能上优于原始算法，具有较好的数值优化能力和应用价值。

Abstract: To address the shortcomings of the original Chinese Pangolin Optimizer in the middle and late stages, including slow convergence, insufficient local exploitation, and limited solution accuracy, an improved Chinese Pangolin Optimizer is proposed in this paper. The proposed method employs chaotic opposition-based initialization to improve the initial population quality, uses a stage-adaptive mechanism to balance early exploration and late exploitation, and introduces differential evolution enhancement together with local refinement to accelerate convergence and improve accuracy. The mean value, standard deviation, and Wilcoxon rank-sum test are used for quantitative analysis. Experimental results demonstrate that the proposed algorithm outperforms the original algorithm in overall performance and shows good potential for numerical optimization applications.