Intelligent Mathematical Modeling of Discharge Coefficient of Nonlinear Weirs With Triangular Plan

In this study, the discharge coefficient (cd) of non-linear weirs with a triangular plan was mathematically modeled using a group of method data handling (gmdh), genetic programming (gp) and multivariate adaptive regression splines (mars) techniques. for this purpose, related datasets including parameters on cd were collected from literature. these methods were selected since they are classified as smart function fitting (sff) methods. the main advantages of sff methods compared to other artificial intelligence methods are defining the most effective parameters on output and assigning more weights to them in mathematical expression process. results of mars indicated that this method with fifteen basic functions could achieve good accuracy for modeling and predicting cd (r²= 0.98 and rmse=0.024). results of gmdh showed that this model includes two hidden layers and that there are five and four neurons at the first and second hidden layers, receptivity. results of developed gp model declared that this model consists of three genes and has acceptable performance for modeling cd. evaluation of proficiency of utilized models with each other indicated that the best accuracy is related to mars model. calculating the discrepancy ratio index (ddr) shows that the minimum range of ddr is related to mars model.