A Hybrid Multi-Strategy Chinese Pangolin Optimization Algorithm and Its Applications

To tackle the drawbacks inherent in the Chinese Pangolin Optimization (CPO) algorithm, such as uneven population initialization distribution and a tendency to fall into local optimal solutions, this paper proposes an ACDCPO algorithm that integrates boundary-adaptive contraction initialization, Cauchy inverse cumulative distribution mutation, and dynamic opposition-based learning strategies, which effectively enhances the uniformity of population distribution, improves the ability to jump out of local optimum, and strengthens the adaptive coordination between exploration and exploitation. To validate its performance, the proposed ACDCPO is compared with nine representative algorithms using the CEC2017 and CEC2022 test functions. The results verify that ACDCPO achieves remarkably higher convergence precision and stability than the comparative algorithms. In four typical engineering optimization tasks, ACDCPO shows strong constraint handling ability and engineering adaptability. In addition, based on near-infrared spectrum data, the ACDCPO algorithm optimized the BP network model for the moisture content prediction of Dendrobium huoshanense, and the coefficient of determination (R2) reached 91.211%, which verified the effectiveness of the method in practical applications.