提前 /拖期调度在 JIT生产中具有重要意义 ,带有交货期窗口的调度问题是一个更一般的问题 ,但目前尚缺乏有效的求解方法。本文提出一种求解带有交货期窗口的单机提前 /拖期调度问题的遗传算法 ,是为克服简单遗传算法的早熟收敛现象而提出的一种新型的遗传算法 ,并用大量随机产生的实例进行了仿真研究 ,结果表明 ,本文提出的算法是有效的 Scheduling in advance / tardiness is of great importance in JIT production. Scheduling with delivery windows is a more general problem, but there is no effective solution. In this paper, we propose a new genetic algorithm to solve the single premature / trafficked scheduling problem with delivery window, which is a new type of genetic algorithm to overcome the premature convergence of simple genetic algorithm, and use a large number of randomly generated examples Simulation results show that the proposed algorithm is effective