Artificial Neural Network to Predict Equilibrium Local Scour Depth around Semicircular Bridge Abutments

Local scour around bridge abutment is a common problem encountered worldwide. Much experimentation has been carried out in this field and the equations derived so far are applicable to particular circumstances only. In this paper, Artificial Neural Network (ANN) approach has been applied to the problem of scour around semicircular bridge abutments. Multilayer Perceptron (MLP) with single hidden layer and Radial Basis Function (RBF) network have been trained with the experimental data from literature and an appropriate model of each of the network is identified. The performance of the developed models has been evaluated using Root Mean Square Error (RMSE) and Correlation Coefficient (CC). A sensitivity analysis of input parameter has been carried out. The accuracy of the trained model has been evaluated against some of the empirical models available in the literature. Experimental results show the suitability and reliability of application of ANN for scour depth prediction around bridge abutments

کلیدواژه ها:

ANN ، MLP ، RBF ، Scour