EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Intelligent Manufacturing Production Line Scheduling Optimization Based on Improved Gray Wolf Optimization Algorithm

Yijia Xu, Jindong Zhao, Yicheng Xu, Shuocheng Sun, Zhe Yang

International Journal of Intelligent Systems · 2026-01 · 2026 (1)

DOI: 10.1155/int/3955742 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Intelligent Systems, online erschienen am 20.11.2026. Verfasst von Yijia Xu und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intelligent manufacturing production line scheduling is formulated as a flexible job shop problem that minimizes the makespan and the total energy consumption. The classical gray wolf optimizer handles this problem poorly because its continuous update does not match the discrete schedule, and it also suffers from random initialization, a fixed local search and late stagnation. This study proposes QM‐IGWO, a Q‐learning–driven multistrategy collaborative improved gray wolf optimizer. Random keys map every wolf to a feasible operation sequence and machine assignment, and an NEH insertion adapted to the flexible job shop seeds both strings. A Q‐learning agent observes the Hamming diversity of the decoded strings and the stagnation level, selects one of four neighborhoods for a local search on the three leaders, and shares the stagnation signal with a selective restart that keeps the Q‐table and an external archive of nondominated schedules. On the Brandimarte benchmark, QM‐IGWO shortens the mean makespan of the classical optimizer by 11.1% and matches or improves the best makespans of a recent hybrid gray wolf optimizer on all ten instances with less than one‐sixth of its evaluation budget. It also leads on the three Hurink subsets, raises the hypervolume by 14.2% over the classical optimizer and by 5.3% over a recent Q‐learning gray wolf optimizer, and shortens the makespan of two automotive parts production lines by 12.3% and 13.1% with about 10% less energy. Holm‐corrected Wilcoxon tests find it significantly better on 94% of the instance‐baseline pairs and never worse.

Zitieren

APA

Xu, Y., Zhao, J., Xu, Y., Sun, S., & Yang, Z. (2026). Research on Intelligent Manufacturing Production Line Scheduling Optimization Based on Improved Gray Wolf Optimization Algorithm. International Journal of Intelligent Systems, 2026(1). https://doi.org/10.1155/int/3955742

Vancouver

Xu Y, Zhao J, Xu Y, Sun S, Yang Z. Research on Intelligent Manufacturing Production Line Scheduling Optimization Based on Improved Gray Wolf Optimization Algorithm. International Journal of Intelligent Systems. 2026;2026(1). doi:10.1155/int/3955742

BibTeX
@article{Xu2026,
  author = {Xu, Yijia and Zhao, Jindong and Xu, Yicheng and Sun, Shuocheng and Yang, Zhe},
  title = {Research on Intelligent Manufacturing Production Line Scheduling Optimization Based on Improved Gray Wolf Optimization Algorithm},
  journal = {International Journal of Intelligent Systems},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/int/3955742}
}
Kostenlos starten →