An expert system with radial basis function neural network based on decision trees for predicting sediment transport in sewers

Apr. 22, 2016

In this study, an expert system with a radial basis function neural network (RBF-NN) based on decision trees (DT) is designed to predict sediment transport in sewer pipes at the limit of deposition. First, sensitivity analysis is carried out to investigate the effect of each parameter on predicting the densimetric Froude number (Fr). The results indicate that utilizing the ratio of the median particle diameter to pipe diameter (d/D), ratio of median particle diameter to hydraulic radius (d/R) and volumetric sediment concentration (C_V) as the input combination leads to the best Fr prediction. Subsequently, the new hybrid DT-RBF method is presented. The results of DT-RBF are compared with RBF and RBF-particle swarm optimization (PSO), which uses PSO for RBF training. It appears that DT-RBF is more accurate (R² = 0.934, MARE = 0.103, RMSE = 0.527, SI = 0.13, BIAS = −0.071) than the two other RBF methods. Moreover, the proposed DT-RBF model offers explicit expressions for use by practicing engineers.

Most popular related searches

Customer comments

No comments were found for An expert system with radial basis function neural network based on decision trees for predicting sediment transport in sewers. Be the first to comment!

Contact

Loading... Drop file here or browse Great, file uploaded. Change File Drop file here or browse

Yes, please send to similar suppliers.

An expert system with radial basis function neural network based on decision trees for predicting sediment transport in sewers

Most popular related searches

Customer comments