【摘要】 针对多目标优化问题提出了一种基于最大最小适应度函数(F maximin)的粒子群算法,将此算法简称为IMP-SO。它在求解多目标问题的非劣解前沿(Pareto Front)时表现出很好的性能。通过经典测试函数计算表明该算法保证收敛到多目标优化问题的Pareto最优前沿;同时,使用两个性能指标(GD和Diversity)验证了此算法优于其他的多目标粒子群优化算法。更多还原

【Abstract】 In this paper,we point to the diversity measurement of Pareto solution in particle swarm optimization,the maximin fitness function including warp ε is put forward.The algorithm named IMPSO has some very desirable properties with regard to multi-objective optimization.Calculation results of benchmark test functions indicate that the algorithm can ensure a better convergence to the true Pareto optimal front,and using GD and Diversity(two testing criteria)to validate the accuracy and diversity of this algorithm.更多还原