论文部分内容阅读
飞行员模拟机复训问题是一个多目标、多资源约束的排班问题,具有较高的复杂度,传统遗传算法无法有效求解该问题。为此,提出一种新的遗传算法,利用基因适应度对交叉、选择操作进行改进,以提高种群的多样性和进化性能。在仿真数据和真实数据上的实验结果表明,该算法有效提高了解的精度,加快了种群的收敛速度。
Pilot simulator recurrent training problem is a multi-objective, multi-resource constrained scheduling problem, with high complexity, the traditional genetic algorithm can not effectively solve the problem. To this end, a new genetic algorithm is proposed to improve the crossover and selection using gene fitness to improve the diversity and evolutionary performance of the population. The experimental results on simulated data and real data show that the algorithm can effectively improve the accuracy of the solution and speed up the convergence of the population.