EUVIMEDEUVIMED entdecken
Crossref

Applying artificial neural network (ANN) models to calculate the roller length of hydraulic jumps in horizontal rectangular channels

Hùng Hồ Việt

Transport and Communications Science Journal · 28.01.2026 · 77 (3) · 254-268

DOI: 10.47869/tcsj.77.3.3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transport and Communications Science Journal, online erschienen am 28.01.2026. Verfasst von Hùng Hồ Việt.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The hydraulic jump roller length plays a decisive role in determining the size and efficiency of energy dissipation structures downstream of spillways and culverts. Therefore, accurate estimation of this parameter is a critical requirement in the design of hydraulic engineering works. This study developed and evaluated eight Artificial Neural Network (ANN) models to predict the hydraulic jump roller length within horizontal prismatic rectangular channels. Four input variables and one model output were selected based on the Buckingham π theorem to ensure representativeness and dimensional homogeneity, an approach that has not been thoroughly investigated previously. In addition, machine learning models were employed to evaluate how gravity, drag, and channel width affect roller length, improving prediction accuracy. Test results show that all ANN models achieved lower errors compared to traditional empirical equations, with Nash–Sutcliffe Efficiency (NSE) coefficients exceeding 0.975. Notably, the two-hidden-layer ANN with 16 neurons per layer attained the highest NSE value (0.992) and the lowest relative error (4.32%), confirming this configuration as the optimal predictive model and a viable alternative to existing empirical methods.

Zitieren

APA

Việt, H. H. (2026). Applying artificial neural network (ANN) models to calculate the roller length of hydraulic jumps in horizontal rectangular channels. Transport and Communications Science Journal, 77(3), 254-268. https://doi.org/10.47869/tcsj.77.3.3

Vancouver

Việt HH. Applying artificial neural network (ANN) models to calculate the roller length of hydraulic jumps in horizontal rectangular channels. Transport and Communications Science Journal. 2026;77(3):254-268. doi:10.47869/tcsj.77.3.3

BibTeX
@article{Vit2026,
  author = {Việt, Hùng Hồ},
  title = {Applying artificial neural network (ANN) models to calculate the roller length of hydraulic jumps in horizontal rectangular channels},
  journal = {Transport and Communications Science Journal},
  year = {2026},
  volume = {77},
  number = {3},
  pages = {254--268},
  doi = {10.47869/tcsj.77.3.3}
}
Kostenlos starten →