EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Self-Adaptive AdamW-Guided Optimization: A Learning-Driven Metaheuristic for Solving Complex Real-World Engineering Problems

Yuhang Xie iD, Wei Li, Cheng Zhong, Shang Gao, Kai Xu, Juanjuan Tu, Bin Qin

Entropy · 09.06.2026 · 28 (6) · 660

DOI: 10.3390/e28060660 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 09.06.2026. Verfasst von Yuhang Xie und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, China. 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: National Natural Science Foundation of China, Jiangsu University of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Given the growing complexity of continuous optimization problems in strongly coupled and black-box environments, this study proposes a novel adaptive gradient-guided metaheuristic, referred to as Self-Adaptive AdamW-Guided Optimization (SAWG). Without requiring explicit gradient information, SAWG constructs population-based pseudo-gradients and systematically integrates key AdamW mechanisms, including adaptive moment estimation, step-size regulation, and weight decay, to guide efficient population updates. Furthermore, a stagnation-aware adaptive control strategy is introduced to alleviate premature convergence and dynamically balance exploration and exploitation. To evaluate the optimization performance of SAWG, experiments were conducted on the CEC2017 and CEC2020 benchmark suites and eight engineering optimization problems. SAWG was also compared with nine other typical and novel high-performance optimizers. Experimental results and statistical analysis show that SAWG achieved excellent optimization performance in most test tasks and maintained strong adaptability and competitiveness in various numerical optimization problems. Therefore, SAWG can be regarded as a high-performance optimizer, providing a novel and effective method for solving complex numerical optimization tasks.

Schlagwörter

Stichwörter der Autor:innen

AdamWbenchmark test suiteengineering design optimizationmetaheuristic optimizationpseudo-gradients

Autor:innen und Institutionen

  • School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, China.
  • Department of Power Engineering, PLA Army Engineering University, Nanjing 210007, China.

ORCID-Profile: Yuhang Xie

Förderung

  • National Natural Science Foundation of China
  • Jiangsu University of Science and Technology

Zitieren

APA

Xie, Y., Li, W., Zhong, C., Gao, S., Xu, K., Tu, J., & Qin, B. (2026). Self-Adaptive AdamW-Guided Optimization: A Learning-Driven Metaheuristic for Solving Complex Real-World Engineering Problems. Entropy, 28(6), 660. https://doi.org/10.3390/e28060660

Vancouver

Xie Y, Li W, Zhong C, Gao S, Xu K, Tu J, et al. Self-Adaptive AdamW-Guided Optimization: A Learning-Driven Metaheuristic for Solving Complex Real-World Engineering Problems. Entropy. 2026;28(6):660. doi:10.3390/e28060660

BibTeX
@article{Xie2026,
  author = {Xie, Yuhang and Li, Wei and Zhong, Cheng and Gao, Shang and Xu, Kai and Tu, Juanjuan and Qin, Bin},
  title = {Self-Adaptive AdamW-Guided Optimization: A Learning-Driven Metaheuristic for Solving Complex Real-World Engineering Problems},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {6},
  pages = {660},
  doi = {10.3390/e28060660}
}
Kostenlos starten →