针对航母舰载机舰面保障作业被抽象为柔性流水车间调度问题后多项作业（工件）难以并行处理的问题，以及现有研究在处理异构舰载机保障作业协同调度方面的局限性，提出了一种决策模型中央调度模块与深度强化学习决策模型相结合的动态并行调度方法。首先将并行的舰载机保障作业时间序列等效转化为串行的逻辑序列，使其适配于柔性流水车间调度问题模型的同时保证作业并行执行的特征；然后基于逻辑序列构建作业调度决策的马尔可夫模型，结合有人机和无人机的作业流程差异，分别为其设计并训练决策模型；同时设计决策模型中央调度模块对两类决策模型进行统一管理，统筹全局阵位、资源、舰载机等态势信息，并下发至各决策模型以对其进行有效协同。最后仿真对比实验显示，相较于以遗传算法为代表的优化计算调度方法，所提算法可在牺牲微小调度性能的情况下大幅提升决策实时性，兼顾了舰载机出动时间和调度方法产出时间，更适用于强实时、高动态环境下的舰载机快速出动任务。

This paper addresses the challenge of parallel processing of multiple tasks (workpieces) in carrier-based aircraft support operations, which are abstracted as a flexible flow shop scheduling problem. It also highlights the limitations of existing research in the collaborative scheduling of heterogeneous carrier-based aircraft. To tackle these issues, we propose a dynamic parallel scheduling method that integrates a central scheduling mechanism with a deep reinforcement learning decision model. Initially, the parallel time series of support operations is equivalently transformed into a serial logical sequence. This transformation ensures compatibility with the flexible flow shop scheduling model while preserving the characteristic of parallel execution. Subsequently, a Markov model for job scheduling decisions is constructed based on the logical sequences, incorporating the operational differences between manned and unmanned aerial vehicles.Distinct decision models are designed and trained for each type of aircraft. Moreover, a central scheduling mechanism is developed to unify the management of these two decision models, coordinating global positioning, resources, and other situational information. This mechanism disseminates information to the respective decision models to facilitate effective collaboration. Finally, simulation comparison experiments indicate that the proposed algorithm significantly enhances decision real-time performance, even at the cost of marginal scheduling efficiency, compared to optimization methods represented by genetic algorithms. The algorithm effectively balances carrier-based aircraft deployment time and the output time of scheduling methods, making it particularly suitable for rapid deployment tasks in high-real-time and dynamic environments.