Particle Swarm Optimization Algorithm Based Feed Forward Neural Network for Uplift Pressure Estimation in Diversion Dams

In this study a procedure for uplift pressure estimation under a diversion dam using Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) algorithm is proposed. Firstly the Laplace equation is solved and piezometric head and uplift pressure are computed under the dam. Then ANN is trained based on PSO algorithm for uplift pressure prediction in different points of considered model and the results are compared with actual data. The inputs and outputs of ANN are coordinates of different points under the dam and corresponding uplift pressures, respectively. The test results show the uplift pressure is predicted with good accuracy

Keywords:

artificial neural network , diversion dam , particle swarm optimization algorithm , uplift pressure