Flexible manufacturing faces the challenge of increasing productivity and conserving resources, especially in complex production environments with dynamic event. This paper addresses a dynamic Hybrid Flow-shop Scheduling Problem (HFSP) with unrelated parallel machines using a Deep Reinforcement Learning (DRL) approach to intelligently allocate continuous new job arrivals while minimizing the total weighted tardiness cost. In this paper, Evolution Strategies-guided Deep Reinforcement Learning (ES-DRL) scheduling model is proposed by designing appropriate state features, scheduling actions, and training strategies. In addition, goal-directed composite rules are proposed to provide effective scheduling actions. Meanwhile, the state transition in the environment is adjusted by introducing key state. The ES-DRL model is then trained to make decisions, indicating the reasoning behind the system design. Experimental results show that ES-DRL outperforms the other comparison algorithms regarding significance. In addition, the experiments are extended to the multi-factories system to further validate the scalability and adaptability of the scheduling model, and this extension also yields encouraging results. These results affirm the universal applicability of ES-DRL for dynamic HFSP.

A chip mounter is the core equipment in the production line of the surface-mount technology, which is responsible for finishing the mount operation. It is the most complex and time-consuming stage in the production process. Therefore, it is of great significance to optimize the load balance and mounting efficiency of the chip mounter and improve the mounting efficiency of the production line. In this study, according to the specific type of chip mounter in the actual production line of a company, a maximum and minimum model is established to minimize the maximum cycle time of the chip mounter in the production line. The production efficiency of the production line can be improved by optimizing the workload scheduling of each chip mounter. On this basis, a hybrid adaptive optimization algorithm is proposed to solve the load scheduling problem of the mounter. The hybrid algorithm is a hybrid of an adaptive genetic algorithm and the improved ant colony algorithm. It combines the advantages of the two algorithms and improves their global search ability and convergence speed. The experimental results show that the proposed hybrid optimization algorithm has a good optimization effect and convergence in the load scheduling problem of chip mounters.

For sudden drinking water pollution event, reasonable opening or closing valves and hydrants in a water distribution network (WDN), which ensures the isolation and discharge of contaminant as soon as possible, is considered as an effective emergency measure. In this paper, we propose an emergency scheduling algorithm based on evolutionary reinforcement learning (ERL), which can train a good scheduling policy by the combination of the evolutionary computation (EC) and reinforcement learning (RL). Then, the optimal scheduling policy can guide the operation of valves and hydrants in real time based on sensor information, and protect people from the risk of contaminated water. Experiments verify our algorithm can achieve good results and effectively reduce the impact of pollution events.