Development and evaluating of two-neural network model (MLP and SVM ) toestimate the Side weir discharge coefficient

ABSTRACT: Prediction and modeling of hydraulic phenomenon is an important part of hydraulicengineering activities. One of the applications of Prediction and modeling is to estimate the dischargecoefficient for hydraulic structures.Side weirs are widely used for flow diversion in irrigation, land drainage, urban sewage systems and alsoin intake structures. There are many ways to calculate flow dischargecoefficientAs experimental methods and computational intelligence. Experimental methods have been considered due to error. Therefore using of soft computing methods to estimate the flow rate is inevitable. In this study to estimate the side weir flow coefficient two model of neural network (MLP and SVM) has been developed.Training and simulation process of these models have been conducted in the Matlabsoftware environment. The results show that the MLP and SVM developed models in comparison with other empiricalequations, has accuracy is very favorable.the performance of MLP model is better than SVM model.