Estimation of Discharge Over the Compound Sharp-Crested Weir using Artificial Neural Networks and Genetic Programming

Abstract

Truncated sharp crested weirs are used to measure flow rate and to control water surface upstream, in irrigation canals and laboratory flumes. The main advantages of such weirs are, ease of construction and capability of measuring a wide range of flows with sufficient accuracy. Artificial neural networks (ANNs) and genetic programming (GP) have recently been used for the estimation of hydraulic data. In this study, they we re used as alternative tools to estimate the discharge of flow over truncated weirs. The hydraulic parameter, including water flow rate Q was determined as functions of the width of crest b, upstream head h, weir height P 1 , the height of triangular weir P 2 and width of flume B. The estimations of the ANN and GP models were found to be in good agreement with the measured data. The results of the ANN model were compared with those of the GP 1 , GP 2 , GP 3 and GP 4 models, show ing that the proposed ANN models are much more accurate than the GP models and GP 4 model has better performance than GP 1 , GP 2 and GP 3 models.