Abstract: Aiming at the problems of slow convergence speed, low optimization accuracy and easy to fall into local optimum of chimp optimization algorithm, a modified chimp optimization algorithm（MChOA） integrating learning behavior strategy is proposed. Firstly, quasi opposition-based learning strategy is used to update the population, increase the diversity and randomness of the population, improve the global search ability of the algorithm, and avoid the algorithm from falling into local optimum. Then, based on the learning behavior strategy of chimps, the individual position of chimps is updated by randomly selecting the “imitation learning” operator or the “emotional induction” operator to enhance the local development ability of the algorithm and speed up the convergence of the algorithm. 16 benchmark functions and 12 CEC2014 are selected for simulation experiment test, the results show that MChOA has higher precision and better optimization performance than traditional ChOA. Finally, the solution of two engineering design problems proves that MChOA has high practical application value in practical engineering problems.

Key words: chimp optimization algorithm, quasi opposition-based learning, learning behavior strategies, benchmark test function, engineering problem solving

摘要： 针对黑猩猩优化算法收敛速度慢、寻优精度低以及容易陷入局部最优的问题，提出融合学习行为策略的改进黑猩猩优化算法（modified chimp optimization algorithm，MChOA）。采用准反向学习策略更新种群，增加种群的多样性和随机性，提高算法全局搜索能力，同时避免算法陷入局部最优。基于黑猩猩学习行为策略，通过随机选择“模仿学习”算子或“情绪感应”算子更新黑猩猩个体位置，增强算法局部开发能力，加快算法的收敛速度。选取16个基准函数以及12个CEC2014进行仿真实验测试，结果表明MChOA与传统ChOA相比具有较高的求解精度和较好的寻优性能。通过两个工程设计问题的求解，证明了MChOA在实际工程问题上也具有较高的实际应用价值。

关键词: 黑猩猩优化算法, 准反向学习, 学习行为策略, 基准测试函数, 工程问题求解