Artificial Intelligence-Based Optimization of Box Culvert Cross-Section Design Under Hydraulic and Structural Constraints
Engineering, Technology & Applied Science Research · 06.06.2026 · 16 (3) · 37040-37047
DOI: 10.48084/etasr.19400 ↗Kurz gefasst
Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 06.06.2026. Verfasst von Cong Chinh Le und 2 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Reinforced concrete box culverts are critical infrastructure for flood management and cross-drainage. However, their conventional design relies on iterative sequential processes that oversimplify the coupling of hydraulic and structural constraints, resulting in overly conservative, costly structures. This study proposes a novel Artificial Intelligence (AI)-based optimization framework that tightly couples hydraulic routing equations with rigorous structural mechanics to minimize total construction. The framework evaluates the performance of two advanced metaheuristic algorithms: Grey Wolf Optimizer (GWO) and the Genetic Algorithm (GA). A comprehensive parametric case study was conducted to assess variations in design discharge and soil cover depth. The results demonstrate that the GWO algorithm successfully navigates the highly constrained non-convex design space, achieving a 24.0% reduction in total cost compared to the conventional deterministic design and outperforming the GA (19.4% reduction). Furthermore, the AI framework autonomously identified critical physical trade-offs, dynamically adapting the culvert aspect ratio to meet strict headwater thresholds during extreme flood events and optimizing member thicknesses across varying live and dead load dominance phases. This automated, performance-based framework provides civil engineers with a robust tool to design cost-efficient, climate-resilient hydraulic structures.
Zitieren
APA
Le, C. C., Le, X. B., & Pham, N. T. (2026). Artificial Intelligence-Based Optimization of Box Culvert Cross-Section Design Under Hydraulic and Structural Constraints. Engineering, Technology & Applied Science Research, 16(3), 37040-37047. https://doi.org/10.48084/etasr.19400
Vancouver
Le CC, Le XB, Pham NT. Artificial Intelligence-Based Optimization of Box Culvert Cross-Section Design Under Hydraulic and Structural Constraints. Engineering, Technology & Applied Science Research. 2026;16(3):37040-37047. doi:10.48084/etasr.19400
BibTeX
@article{Le2026,
author = {Le, Cong Chinh and Le, Xuan Bao and Pham, Ngoc Thinh},
title = {Artificial Intelligence-Based Optimization of Box Culvert Cross-Section Design Under Hydraulic and Structural Constraints},
journal = {Engineering, Technology & Applied Science Research},
year = {2026},
volume = {16},
number = {3},
pages = {37040--37047},
doi = {10.48084/etasr.19400}
}
EUVIMED