The pickup and delivery hybrid-operations of AGV conflict-free scheduling problem with time constraint among multi-FMCs

Since much emphasis has been put on the eco-friendly manufacturing process in industries, and the complex changes in market demands, this paper focuses on a green scheduling problem of automated guided vehicles (AGVs) in a flexible manufacturing system (FMS). The studied FMS consists of multi-FMCs (flexible manufacturing cells) which have many material handling needs with time constraints. Distinguished from other AGV scheduling problems in FMS, this paper concentrates on the pickup and delivery operations or even bi-handling requirements of AGVs for FMCs, ignoring the inner production process within them. To solve this problem, a bi-objective mathematical model is built trying to minimize the total tardiness and energy consumption of AGVs simultaneously. Some properties of the problem and a no-collision algorithm are developed for the potential conflicts among AGVs. Due to the NP-hard nature of the proposed problem, a hyper-heuristic (HH) algorithm based on a double deep Q network (DDQN) is introduced, which benefits from the structures of double decision networks and multi-operator. To improve the performance of the proposed algorithm, the experience pool is used to increase the convergence speed and the crowding distance, and the non-dominated sorting strategies are presented to decide the acceptance of the new generation. Besides, in the DDQN, the states and rewards of agents are designed based on the characteristics of the scheduling problem. Finally, many experiments have been conducted and the computational results reveal that the proposed DDQN-HH algorithm outperforms the other two compared algorithms in both the convergence speed and quality of solutions.