提出一种带两类正态变异的多目标粒子群算法,其中一类变异有助于在非劣解的邻域内发现新的非劣解,另一类变异可以分散粒子群.将搜索过程分为3个阶段,在每个阶段引导粒子的选择采用不同的针对性策略.数值结果表明,所提出的算法能够显著提高解的多样性和收敛性. This paper proposes a multi-objective particle swarm optimization algorithm with two types of normal variation, in which one type of mutation helps to find new non-inferior solutions in the neighborhood of non-inferior solutions and the other can disperse the particle swarm. For each of the three stages, different strategies are used to guide the selection of particles at each stage.The numerical results show that the proposed algorithm can significantly improve the diversity and convergence of solutions.