A Dual-Stream Deep Reinforcement Learning Framework for Hot Rolling Production Scheduling
Machines · 30.06.2026 · 14 (7) · 741
DOI: 10.3390/machines14070741 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 30.06.2026. Verfasst von Chi Wang und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSFC, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Hot Rolling Production Scheduling (HRPS) is a crucial combinatorial optimization problem characterized by severe conflicts between rigid physical rolling rules and strict order due dates. While real-time scheduling is essential for dynamic manufacturing, traditional meta-heuristics suffer from severe computational time bottlenecks. Conversely, standard end-to-end Deep Reinforcement Learning (DRL) models offer rapid inference but typically struggle with spatio-temporal feature entanglement, training instability under extreme penalty landscapes, and poor zero-shot scale generalization. To bridge these gaps, this paper proposes a novel framework named Dual-Stream Group-Optimize Policy Optimization with Multiple Optima (DSGO-POMO). The framework introduces three core innovations: (1) a Dual-Stream intervention network that explicitly decouples and synergistically fuses physical attributes with temporal slacks; (2) a Group Relative Policy Optimization (GRPO) training mechanism to stabilize policy updates; and (3) an Entropy-Aware and Dual-Annealed Differential Active Search (EA-DAS) strategy to seamlessly adapt pre-trained weights to out-of-distribution scales. Extensive computational experiments validate the superiority of the proposed framework. On medium-scale instances (n=50), the basic DSGO-POMO slashes inference time to merely 0.09 min compared to the approximately 46 min required by classical heuristics while simultaneously achieving lower total costs. Furthermore, during zero-shot extrapolation on ultra-large instances (n=200), the framework coupled with EA-DAS outperforms the best heuristic baseline by 14.7% in solution quality and completes the search in under 2 min. These numerical breakthroughs confirm that DSGO-POMO provides a blazing-fast, highly robust, and industrially viable rescheduling paradigm.
Förderung
- NSFC
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Wang, C., Cao, W., & Huang, M. (2026). A Dual-Stream Deep Reinforcement Learning Framework for Hot Rolling Production Scheduling. Machines, 14(7), 741. https://doi.org/10.3390/machines14070741
Vancouver
Wang C, Cao W, Huang M. A Dual-Stream Deep Reinforcement Learning Framework for Hot Rolling Production Scheduling. Machines. 2026;14(7):741. doi:10.3390/machines14070741
BibTeX
@article{Wang2026,
author = {Wang, Chi and Cao, Wang and Huang, Min},
title = {A Dual-Stream Deep Reinforcement Learning Framework for Hot Rolling Production Scheduling},
journal = {Machines},
year = {2026},
volume = {14},
number = {7},
pages = {741},
doi = {10.3390/machines14070741}
}
EUVIMED