EUVIMEDEUVIMED entdecken
Crossref

Hybrid Intelligent Multi-Objective Dynamic Optimization Based on MOEPSO-GA

Jun Fu, Linqing Du, Huan Li

IEEE Transactions on Automation Science and Engineering · 2026 · 23 · 9637-9655

DOI: 10.1109/tase.2026.3685255 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Automation Science and Engineering, 2026. Verfasst von Jun Fu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, a hybrid intelligent optimization method based on multi-objective enhanced particle swarm optimization-genetic algorithm (MOEPSO-GA) is proposed for solving multi-objective dynamic optimization problem. This method innovatively combines the global search capability of heuristic algorithms with the high precision and guaranteed optimality of deterministic algorithms, ensuring an evenly distributed Pareto front. Firstly, a global dual optimal selection mechanism is introduced, utilizing a genetic algorithm to balance the diversity and convergence of non-dominated solutions. Secondly, an adaptive flight parameter adjustment mechanism is designed to assist particles in adaptively selecting learning modes, thereby balancing the global exploration and local development capabilities. Thirdly, the optimal replacement mechanism significantly enhances population diversity, enabling MOEPSO-GA to rapidly explore non-dominated regions. Fourthly, the adaptive $\varepsilon $ -constraint method is combined with sequential quadratic programming to optimize the non-dominated set explored by MOEPSO-GA, promoting rapid convergence to the true Pareto front and thereby reducing computational costs. Finally, the effectiveness and superiority of the proposed algorithm are validated through numerical simulations and comparisons with state-of-the-art algorithms. Note to Practitioners—The motivation for this work is to develop an effective optimization method for the ubiquitous multi-objective dynamic optimization problem across various industries. This problem involves balancing multiple conflicting objectives within dynamic systems, such as optimizing yield and resource consumption in bioprocessing or managing supply and demand in power systems. Existing methods often struggle to meet the demands of computational complexity and real-time adaptability, making it challenging to effectively address this problem in practical scenarios. Therefore, this study aims to effectively explore the non-dominated solution space while considering system dynamics, which are two critical requirements. Based on multi-optimization mechanisms in multi-objective optimization algorithms and numerical optimization methods, we propose an efficient hybrid intelligent multi-objective dynamic optimization method that rapidly explores the non-dominated region and uniformly converges to the Pareto front with guaranteed optimality.

Zitieren

APA

Fu, J., Du, L., & Li, H. (2026). Hybrid Intelligent Multi-Objective Dynamic Optimization Based on MOEPSO-GA. IEEE Transactions on Automation Science and Engineering, 23, 9637-9655. https://doi.org/10.1109/tase.2026.3685255

Vancouver

Fu J, Du L, Li H. Hybrid Intelligent Multi-Objective Dynamic Optimization Based on MOEPSO-GA. IEEE Transactions on Automation Science and Engineering. 2026;23:9637-9655. doi:10.1109/tase.2026.3685255

BibTeX
@article{Fu2026,
  author = {Fu, Jun and Du, Linqing and Li, Huan},
  title = {Hybrid Intelligent Multi-Objective Dynamic Optimization Based on MOEPSO-GA},
  journal = {IEEE Transactions on Automation Science and Engineering},
  year = {2026},
  volume = {23},
  pages = {9637--9655},
  doi = {10.1109/tase.2026.3685255}
}
Kostenlos starten →