Estimating the energy dissipation of flow passing over triangular and trapezoidal plan weirs using the GMDH model

Abstract Weirs are one of the most common hydraulic structures used in water engineering projects. In this research, a group method data handling (GMDH) was developed to estimate energy dissipation flow passing over labyrinth weirs with triangular and trapezoidal plans. To compare performance model other types soft computing models, multilayer perceptron neural network (MLPNN) developed. The dimensionless parameters derived from dimensional analysis, including relative upstream head (ho/P), number cycles (Ncy), Froude ( Fr), magnification ratio (Mr) were as input variables. error statistical indicators GMDH training phase R2 = 0.913, RMSE 0.010, testing 0.829, 0.015. MLPNN 0.957, 0.007, 0.945, 0.009. Examining structure shows that ho/P, Ncy, Mr play more meaningful roles development network.