Prediction of discharge coefficient of side weir using adaptive neuro-fuzzy inference system

Abstract

Predicting the discharge coefficient of the hydraulic structures is one of the main subjects related to the hydro-system management. Weirs are the common hydraulic structure widely used in the water engineering projects. Side weir is the common type of hydraulic structure used in water engineering projects. Principal component analysis of the affective parameters on the side weir discharge coefficient leads to develop optimal structure for the empirical formulas and artificial intelligent models. In this paper, the principal component analysis (PCA) technique was used to define the most important affective parameters on the discharge coefficient of side weir (\({\text{Cd}}_{\text{sw}}\)). The result of the PCA showed that the Froude number and ratio of the weir height to the upstream flow depth (P/h1) are the most influential parameters affecting the \({\text{Cd}}_{\text{sw}}\). Developing the adaptive neuro-fuzzy inference system (ANFIS) based on the PCA result showed that the optimal ANFIS structure is related to consider the five and four Gaussian membership function for the Froude number and P/h1 parameters, respectively. The correlation coefficient of the ANFIS model during the training and testing stage was found to be 0.96 and 0.86 correspondingly.