Prediction of discharge coefficients for broad-crested weirs using expert systems

ABSTRACT

Broad crested weirs can be used to make discharge measurements in irrigation canals; the entrance of stepped weirs or chutes are sometimes designed as a broad crested weir structure. These structures are also sometimes used for the dam body. In this study, the Artificial Neural Network (ANN) and M5 model tree methods are used to predict discharge coefficients (C_d) for broad crested weirs. The results from these two models are compared with nonlinear regression equations. Four series of data obtained from different rectangular broad crested weirs have been used and important dimensionless parameters have been defined. Results show that the ANN procedure is superior to the M5 model and regression approaches. The accuracy for ANN is quantified by R = 0.966 and RMSE = 0.038. All the three methods are able to provide a reasonable prediction for C_d; the M5 model tree provides four linear equations that can be used to estimate C_d. The shape of the C_d contours shows that the effect of weir height (P) exceeds that of the weir length (L).

KEYWORDS:

• Discharge coefficient
• broad crested weir
• artificial neural network
• nonlinear regression
• m5 model tree

Nomenclature

L= weir length (m);

P= weir height (m);

Q = discharge (m³/s);

H₁ =upstream total head (m);

H =water depth over weir crest (m);

C_d =discharge coefficient (dimensionless);

T=a set of examples (dimensionless);

T_i =the subset of examples (dimensionless);

S_d =standard deviation (dimensionless)

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Acknowledgments

This paper is the outcome of a research project supported by the University of Tabriz research affairs office.

Disclosure statement

The authors declare that they have no conflict of interest.