Wave Optics Optimizer: A novel meta-heuristic algorithm for engineering optimization

•Proposes a meta-heuristic algorithm based on the Fraunhofer diffraction experiment.•Designs dynamic parameters and explores 20 hyperparameter combinations for balance.•Designs multiple update strategies to enhance escape from local optima.•Evaluates performance using 3 CEC suites and 7 engineering...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Communications in nonlinear science & numerical simulation Ročník 152; s. 109337
Hlavní autoři: Peng, Yong, Gu, Shaowei, Liang, Yunbin, Ouyang, Kaichen, Li, Yingli, Wang, Kui, Wu, Guohua, Fan, Chaojie
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.01.2026
Témata:
Engineering optimization
Meta-heuristic
Numerical optimization problem
Physics-based algorithm
Wave optics optimizer
Numerical optimization problem
Wave optics optimizer
Meta-heuristic
Physics-based algorithm
Engineering optimization
ISSN:1007-5704
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Proposes a meta-heuristic algorithm based on the Fraunhofer diffraction experiment.•Designs dynamic parameters and explores 20 hyperparameter combinations for balance.•Designs multiple update strategies to enhance escape from local optima.•Evaluates performance using 3 CEC suites and 7 engineering optimization problems.•Demonstrates superiority over 11 classical, 11 improved, and 9 high-performance optimizers. [Display omitted] With the advancement of technology, numerical optimization problems have become increasingly complex, and meta-heuristics have gradually emerged as effective tools for tackling such challenges. Therefore, this paper proposes a novel meta-heuristic called the Wave Optics Optimizer (WOO). WOO is inspired by the Fraunhofer diffraction experiment, which reveals the wave nature of light. In WOO, each light wave corresponds to a candidate solution. During the optimization process, solutions leverage the diffraction and interference effects of light to explore the search space and gradually move toward the global optimal solution (central bright fringe). Specifically, the diffraction effect simulates the propagation characteristics of light waves passing through a slit, enhancing the diversity of the initial solutions, while the interference effect facilitates communication and learning among the population, guiding convergence toward superior regions. Thanks to these properties, WOO is capable of efficiently searching in complex optimization environments while improving solution stability and accuracy. To evaluate WOO’s optimization capability, experiments were conducted on 3 CEC suites (CEC2014, CEC2017, CEC2022) and 7 engineering optimization problems. WOO was compared against 11 classical optimizers, 11 improved optimizers, and 9 high-performance CEC optimizers. Experimental results and statistical analysis demonstrate that WOO achieves superior optimization performance in most test tasks, maintaining strong adaptability and competitiveness across various types of numerical optimization problems. Therefore, WOO can be regarded as a high-performance optimizer, providing a novel and effective approach for solving complex numerical optimization tasks. The source code of WOO is publicly accessible at: https://drive.mathworks.com/sharing/b03a109a-c7b9-4bc8-aba9-4540816aa5cb
ISSN:1007-5704
DOI:10.1016/j.cnsns.2025.109337