Potential of particle swarm optimization based radial basis function network to predict the discharge coefficient of a modified triangular side weir

Estimating the discharge coefficient is one of the most important steps in the process of side weir design. In this paper, the particle swarm optimization algorithm and radial basis neural network are combined (RBFN-PSO) and employed to model the discharge coefficient of a modified triangular side weir. The developed RBF network has five neurons in the input layer and one neuron in the output layer. The inputs include a wide range of non-dimensional geometrical and hydraulic parameters of a modified triangular side weir, and the output is the discharge coefficient. The RBFN-PSO performance is evaluated using published experimental results and compared with the backpropagation radial basis function network (RBFN-BP) by using the statistical indexes Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and average absolute deviation (%δ). According to the results, the PSO algorithm successfully improved the RBFN while the RBFN-PSO model's generalization capacity enhanced, with RMSE of 0.071 compared to the RBFN-BP model with RMSE of 0.114 in the testing dataset.