EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Solving Flexible Job-Shop Scheduling Problem with Heterogeneous Graph Neural Network Based on Relation and Deep Reinforcement Learning

Hengliang Tang, Jinda Dong

Machines · 22.08.2024 · 12 (8) · 584

DOI: 10.3390/machines12080584 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 22.08.2024. Verfasst von Hengliang Tang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Outstanding Young Science and Technology Worker of Science and Technology Projects in Tongzhou District, General Program of Science and Technology Development Project of Beijing Municipal Education Commission of China, School level Youth Research Fund Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Driven by the rise of intelligent manufacturing and Industry 4.0, the manufacturing industry faces significant challenges in adapting to flexible and efficient production methods. This study presents an innovative approach to solving the Flexible Job-Shop Scheduling Problem (FJSP) by integrating Heterogeneous Graph Neural Networks based on Relation (HGNNR) with Deep Reinforcement Learning (DRL). The proposed framework models the complex relationships in FJSP using heterogeneous graphs, where operations and machines are represented as nodes, with directed and undirected arcs indicating dependencies and compatibilities. The HGNNR framework comprises four key components: relation-specific subgraph decomposition, data preprocessing, feature extraction through graph convolution, and cross-relation feature fusion using a multi-head attention mechanism. For decision-making, we employ the Proximal Policy Optimization (PPO) algorithm, which iteratively updates policies to maximize cumulative rewards through continuous interaction with the environment. Experimental results on four public benchmark datasets demonstrate that our proposed method outperforms four state-of-the-art DRL-based techniques and three common rule-based heuristic algorithms, achieving superior scheduling efficiency and generalization capabilities. This framework offers a robust and scalable solution for complex industrial scheduling problems, enhancing production efficiency and adaptability.

Förderung

  • Outstanding Young Science and Technology Worker of Science and Technology Projects in Tongzhou District
  • General Program of Science and Technology Development Project of Beijing Municipal Education Commission of China
  • School level Youth Research Fund Project

Zitieren

APA

Tang, H., & Dong, J. (2024). Solving Flexible Job-Shop Scheduling Problem with Heterogeneous Graph Neural Network Based on Relation and Deep Reinforcement Learning. Machines, 12(8), 584. https://doi.org/10.3390/machines12080584

Vancouver

Tang H, Dong J. Solving Flexible Job-Shop Scheduling Problem with Heterogeneous Graph Neural Network Based on Relation and Deep Reinforcement Learning. Machines. 2024;12(8):584. doi:10.3390/machines12080584

BibTeX
@article{Tang2024,
  author = {Tang, Hengliang and Dong, Jinda},
  title = {Solving Flexible Job-Shop Scheduling Problem with Heterogeneous Graph Neural Network Based on Relation and Deep Reinforcement Learning},
  journal = {Machines},
  year = {2024},
  volume = {12},
  number = {8},
  pages = {584},
  doi = {10.3390/machines12080584}
}
Kostenlos starten →