Robust scheduling based on deep reinforcement learning for flexible job shop with machine breakdown and new job arrival

Abstract With the increasing personalized product demand and additional new orders from customers, the new job arrival and machine breakdown caused by overload have become common production disturbances, inevitably affecting the initial production plan. To maintain the stability of the scheduling for dynamical flexible job shops with machine breakdown and new job arrival, this paper proposes a robust scheduling strategy that is designed with a flexible network structure and dual-action chained cooperative decision-making mechanism based on deep reinforcement learning (FD-DRL). Firstly, a flexible neural network structure is innovatively constructed, which embeds the feature vector into operation nodes to design a dynamic production state extraction method with graph neural networks (GNN). Secondly, the dual-action chained cooperative decision-making mechanism is established for agents, who consider the new and remaining operations overall to maximize the utilization of machine idle time. Finally, through training and verification, the effectiveness and advancement of the proposed FD-DRL method is verified by comparing with heuristic/meta-heuristics and the static model of deep reinforcement learning (DRL).