提出一种基于进化知识融合的多目标人工蜂群算法.首先,采用精英群体知识和种群自身进化知识混合引导引领蜂进化,保持种群的多样性和优异性;然后,将一种融合个体支配关系和种群分布关系的方法引入跟随蜂的概率选择中,合理选择个体进行深度开发以改善算法收敛性能和分布性能;最后,提出一种更为严格的外部档案维护策略以降低外部档案维护成本,提高解集的分布性能.通过求解标准测试函数,并与其他3种多目标优化算法进行比较,仿真结果表明所提出算法具有良好的收敛性能和分布性能,且解集的覆盖范围更广. This paper proposes a multi-objective artificial bee colony algorithm based on evolutionary knowledge fusion.Firstly, the elite population knowledge and the population’s own evolutionary knowledge are used to guide and guide the bee evolution to maintain the diversity and superiority of the population. Then, a multi-objective artificial bee colony And the distribution of population are introduced into the probabilistic selection of bees followed by a reasonable choice of individuals for further development to improve the convergence performance and distribution performance of the algorithm. Finally, a more stringent external file maintenance strategy is proposed to reduce the external file maintenance costs and improve By solving the standard test function and comparing with other three kinds of multi-objective optimization algorithms, the simulation results show that the proposed algorithm has good convergence performance and distribution performance, and the solution set has a wider coverage.