Potential of radial basis function network with particle swarm optimization for prediction of sediment transport at the limit of deposition in a clean pipe

Abstract

The essential minimum velocity required to prevent sediment deposition was predicted in this study using soft computing. The Radial Basis Function (RBF) network was utilized, and particle swarm optimization (PSO) was used to determine the radial basis function (RBF) parameters. The factors that influence sediment transport to the limit of deposition are determined first, and they are classified in different dimensionless groups. Then, different models are presented in order to consider the effect of each of the dimensionless parameters. The densimetric Froude number (Fr) was predicted through using RBFN-PSO. The results of RBFN-PSO also were compared with the results of RBFN-BP, indicating that RBFN-PSO is more accurate than RBFN-BP and predicts Fr with an acceptable level of accuracy (RMSE = 0.037, MARE = 0.092). Also, a sensitivity analysis is employed to assign the most significant variable for the Fr prediction.