The scheduling problems in mass production, manufacturing, assembly, synthesis, and transportation, as well as internet services, can partly be attributed to a hybrid flow-shop scheduling problem (HFSP). To solve the problem, a reinforcement learning (RL) method for HFSP is studied for the first time in this paper. HFSP is described and attributed to the Markov Decision Processes (MDP), for which the special states, actions, and reward function are designed. On this basis, the MDP framework is established. The Boltzmann exploration policy is adopted to trade-off the exploration and exploitation during choosing action in RL. Compared with the first-come-first-serve strategy that is frequently adopted when coding in most of the traditional intelligent algorithms, the rule in the RL method is first-come-first-choice, which is more conducive to achieving the global optimal solution. For validation, the RL method is utilized for scheduling in a metal processing workshop of an automobile engine factory. Then, the method is applied to the sortie scheduling of carrier aircraft in continuous dispatch. The results demonstrate that the machining and support scheduling obtained by this RL method are reasonable in result quality, real-time performance and complexity, indicating that this RL method is practical for HFSP.

Carrier-based aircraft maintenance tasks are conducted in time-critical, resource-constrained, and uncertain environments. Optimizing the scheduling allocation scheme of maintenance personnel and equipment, reasonably responding to uncertainty disturbances, and maintaining a high fleet availability are vital to the combat and training missions of carrier-based aircraft. The maintenance task scheduling problem for carrier-based aircraft is investigated in this study. First, a mathematical model for comprehensive carrier-based aircraft maintenance task scheduling that considers constraints such as maintenance personnel, equipment/shop, space, and parallel capacity is developed. Second, to generate the baseline scheduling scheme, an improved non-dominated sorting genetic algorithm II (I_NSGA-II) with local neighborhood search is proposed for the model optimization solution; I_NSGA-II uses the serial scheduling generation scheme mechanism to generate the time sequence scheduling scheme for maintenance personnel and equipment/workshop of different fleet sizes. Third, to cope with dynamic uncertainty disturbances, two reactive scheduling methods, i.e., complete rescheduling and partial rescheduling, are proposed to perform reactive scheduling corrections to the baseline schedule. Case simulation shows that the established mathematical model is reasonable and practical, and that the proposed I_NSGA-II is superior to the current mainstream algorithms. In addition, the decision maker can select between the two reactive scheduling methods flexibly based on the different forms and scales of disturbance.