THE HYDRODYNAMIC BEHAVIOR OF HADITHA DAM SPILLWAY UNDER DIFFERENT CONDITIONS

Abstract

Spillways are designed to release surplus water over a maximum storage. The excess water flows from the top of the reservoir and is carried back to the river by a spillway. Many radial gates were destroyed under hydrodynamic load. Radial gate connectors are susceptible to fatigue failure due to excessive vibration; therefore, gate vibration during operation must be investigated to confirm safe operation at the design water pressure. Several studies were carried out to analyses and simulate the flow over the spillway. In present study, the flow pattern over Haditha dam spillway has been simulated using computational fluid dynamics (CFD). CFD provides a numerical approximation to solve the governing equation of fluid movement. The numerical model was performed using Ansys Fluent 2020 R1 to simulate the flow properties; and determination of cavitation damage at three discharges corresponding in the design of Haditha dam which are 4700, 7140, and 7900 m3/s. In addition to investigate the effect of gate vibration under dynamic water loads. The Realisable k-ɛ turbulence model was utilized with the volume of fluid (VOF) model to simulate the interaction between air and water phases. The validation of the numerical model was achieved by comparing it with a physical model. The physical model of the Haditha Dam spillway was made from iron with a scale of 1:110. It has been designed and constructed in a hydraulic laboratory according to the modelling principle of the hydraulic structures. The strains on any structure is a critical issue worldwide, resulting from loads on the structure. An exact prediction at all the expected strains ranges on the dam will pave the way for better dam management under different discharges. The artificial neural network (ANN) technique has been used to study the behavior of strains on the dam and to create a model which can be used to predict the strain on the model of Haditha dam. The ANN is a computational model that simulates the method neurons work in human brain. The research includes a study of the strains on the dam body and the gate. The input of the present model includes gate opening, discharge, depth of upstream water, and force on the dam body and gate. The model has been applied by using about 150 actual tests of strain in the hydraulic laboratory. The model has been achieved by using a MATLAB software with hyperbolic sigmoid transfer function and three nodes. The accuracy of the model was achieved by using several statistical indicators such as root mean square error (RMSE) and main absolute error (MAE). The present study showed a high agreement between the results of physical and numerical model; and the k-ɛ turbulence model could simulate the Haditha dam spillway with low cost and short times. The cavitation damage may occur at the region start at the end of the arching spillway to stretches downstream, and there is no damage of gate vibration under dynamic water load. On the other hand, the ANN is capable of predicting the strain on Haditha dam with high accuracy. The regression for both strains on the dam body and the gate was where than 89% for all training, validation, testing, and all samples. Finally, for both strain models on the dam body and the gate, the most influential input variable is the gate opening, followed by discharge, force, and depth of upstream water. The influence of a gate opening reached about 60%, 40% for the strain on the gate and body dam respectively.