Intelligent estimation of maximum local scour depth around L-head groynes by Artificial Neural Networks and Adaptive Neuro Fuzzy Inference System (ANFIS)

A local scouring phenomenon is one of the important problems in hydraulic design of groynes. Due to constriction and downward flow, the scouring can occur around the groynes. Nowadays, the artificial neural networks have a lot of applications in various water engineering problems where there is not any specific relation between effective parameters. In this study, the Artificial Neural Networks (ANNs) and Adaptive Neuro Fuzzy Inference System (ANFIS) were used for estimating the maximum depth of scour around L-head groynes. The results were compared with experimental relations. One hidden layer with five neurons was used for ANNs. The activation function for hidden layer was tangent hyperbolic while for output layer was sigmoid function. The first order Sugeno fuzzy model with hybrid learning algorithm was used in ANFIS. The correlation coefficient of test data for ANNs, ANFIS and experimental relation were 0.97, 0.99 and 0.93 respectively. The comparison of results with experimental relation showed the ability of artificial intelligent system (especially ANFIS) for learning and estimatign maximum depth of scour around L-head groynes.