为求解多目标优化问题,将快速非支配进化算法(NSGA-Ⅱ)进行了推广,构造了一种新的多目标指数罚函数,将其作为NSGA-Ⅱ算法的适应度函数,通过每次自适应更新罚因子,以此获得多目标规划问题的有效解(Pareto解).仿真结果表明,该算法在快速收敛的情况下,能够获得更加均匀的Pareto前沿.
In order to solve multi-objective programming problem ,this paper extended the NSGA-II algorithm ,and constructed a new multi-objective exponential of penalty function as the fitness function of NSGA-II algorithm .It could to obtain the Pareto solutions of multi-objective program‐ming problem through dynamic updating penalty factor .Finally ,the simulation results showed that the algorithm not only converged fastly ,but also obtained more uniform Pareto frontier .