本文对最小化完工时间并行多机调度问题提出了一种基于组合规则的遗传算法 .用遗传算法来优化调度策略 ,使得在不同的调度阶段 ,可采用不同的调度规则以提高算法性能 ,并用计算实例表明了该遗传算法优于基于机器编码的模拟退火算法和遗传算法 ,并能适用于大规模并行多机调度问题 ,算法计算量小 ,鲁棒性强 . In this paper, we propose a genetic algorithm based on combinatorial rules to minimize the completion time of parallel multi-machine scheduling problem.Genetic algorithm is used to optimize the scheduling strategy so that different scheduling rules can be used to improve the performance of the algorithm in different scheduling stages, The example shows that the genetic algorithm is superior to the machine - code - based simulated annealing algorithm and genetic algorithm, and can be applied to large - scale parallel multi - machine scheduling problem. The algorithm has low computational complexity and strong robustness.