基于GA的飞行员模拟机排班问题求解

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。

Solution of Pilot Simulator Timetable Problem Based on Genetic Algorithm

The pilot simulator scheduling problem is a multi-objective and multi-constrained timetable problem. High complexity of the problem makes it impossible to solve it by using traditional Genetic Algorithm（GA）. This paper proposes an improved GA. The new crossover and reproduction operator, which are redesigned by gene fitness, effectively increases the diversity and the evolution performance of the population. Experimental results based on simulation data and real data show that the improved algorithm can increase the precision of solutions and convergence speed of the population.