A Sliding-Window-Based Reinforcement Learning for Dynamic Assembly Flow Shop Scheduling with Multi-Product Delivery
Advancing real-time manufacturing efficiency through sliding-window reinforcement learning and graph-based modeling.
Multi-product kitting delivery imposes significant challenges for real-time scheduling in hybrid manufacturing systems that integrate processing and assembly, as dynamic order arrivals simultaneously alter supply dependencies and the set of feasible job-machine assignments. This ...
ArXiv CS.AI
Source
Generated insight by OnAirToday AI
This research introduces a novel sliding-window reinforcement learning framework that successfully navigates the complex, sparse reward landscapes inherent in hybrid manufacturing environments. By effectively modeling bottleneck dynamics, this approach provides a scalable solution for real-time scheduling that outperforms traditional heuristic methods.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.