遗传算法在多目标优化问题中的应用策略

GA application strategy of multi-objective optimization

遗传算法针对多目标优化问题,在适应度函数的选择、为防止遗传漂移和维持种群多样性等方面采用了相应的策略.在两杆构架优化的实例中,根据关系算子进行Pareto最优性排序,计算个体的适应度;引入分享机制以避免遗传漂移现象,保持种群的多样性;从种群池中独立保持Pareto解,使得最优解成为实际上的满意解.

Aimed at the multi-objective optimization problem with GA, a corresponding strategy was employed in connection with the selection of fitness function, genetic drift and maintenance of population diversity. In an illustrative optimization of two-bar truss, the Pareto optimal ordering was performed according to relationship operator, individual fitness was calculated, a share system was set up in order to avoid the generic drift and maintain the population diversity, and the Pareto solution was independently kept from the population pool so that the optimal solution was actually made a satisfactory one.