Towards a New Design Equation for Piano Key Weirs Discharge Capacity

Piano Key weirs are Labyrinth like weirs which can be placed on the top of gravity dams. They represent a powerful solution to increase the discharge capacity of existing dam spillways. For proper design it is necessary to accurately predict this discharge capacity. In this research, artificial neural network, multiple linear and nonlinear regressions are used to set up a new design equation for the discharge capacity of Piano Key weirs. The effect of each parameter on the discharge capacity of Piano Key weirs is tested in these models. Several non-dimensional parameters are used to define a functional relationship between the inputs and output. These parameters are built from the geometric dimensions of the structure such as weir height, inlet and outlet keys width, overhangs length, water head and side crest length. Previous experimental data, which were collected at the experimental laboratory of the research group Hydraulics in Environmental and Civil Engineering (HECE), University of Liege, are used for training and testing patterns of the models. Root mean square errors (RMSE) and coefficient of determination (R2) are used as comparing criteria for the evaluation of the models. The models’ results are compared with experimental results and other existing equations.