EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Kepler Optimization Algorithm Based on Q-Learning for Solving Permutation Flow Shop Scheduling Problems

Xiangbo Qi, Zhijing Zhang, Jiaxi Zhang, Yan Song

IEEE Access · 2026 · 14 · 78242-78259

DOI: 10.1109/access.2026.3693629 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Xiangbo Qi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Liaoning Provincial Department of Science and Technology Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The permutation flow shop scheduling problem (PFSP) is a significant challenge in production scheduling, considerably impacting industrial efficiency and competitiveness. To minimize the makespan in PFSP, this paper proposes a hybrid Kepler optimization algorithm (H-KOA) that incorporates a Q-learning mechanism and multiple enhancement strategies. The core innovation is the integration of Q-learning, which adaptively and dynamically adjusts key algorithm parameters via reinforcement learning, thereby effectively balancing global exploration and local exploitation. Furthermore, the H-KOA employs the Nawaz-Enscore-Ham (NEH) heuristic to generate a high-quality initial solution and integrates a local search strategy to deepen its exploitation capability. To evaluate the Q-learning mechanism, comprehensive ablation experiments are conducted. Comparative experiments with other advanced intelligent optimization algorithms are performed using standard benchmark instances. The results demonstrate the significant advantages of the proposed H-KOA in solving PFSP. Its practicality and effectiveness are further validated through an application to the production scheduling of straight-seam steel pipes.

Förderung

  • Liaoning Provincial Department of Science and Technology Project

Zitieren

APA

Qi, X., Zhang, Z., Zhang, J., & Song, Y. (2026). A Hybrid Kepler Optimization Algorithm Based on Q-Learning for Solving Permutation Flow Shop Scheduling Problems. IEEE Access, 14, 78242-78259. https://doi.org/10.1109/access.2026.3693629

Vancouver

Qi X, Zhang Z, Zhang J, Song Y. A Hybrid Kepler Optimization Algorithm Based on Q-Learning for Solving Permutation Flow Shop Scheduling Problems. IEEE Access. 2026;14:78242-78259. doi:10.1109/access.2026.3693629

BibTeX
@article{Qi2026,
  author = {Qi, Xiangbo and Zhang, Zhijing and Zhang, Jiaxi and Song, Yan},
  title = {A Hybrid Kepler Optimization Algorithm Based on Q-Learning for Solving Permutation Flow Shop Scheduling Problems},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {78242--78259},
  doi = {10.1109/access.2026.3693629}
}
Kostenlos starten →