Evaluation of Artificial Intelligent Methods to Release Sediments from Reservoirs by Pressurized Flushing

Sedimentation in reservoirs is an important issue that should be considered for the reservoirs operation and useful life. In this study, application of the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN) in prediction of the sediment release from the bottom outlet using semi-cylinder for different variables was evaluated. Dimensionless parameters such as dimensionless length and height of the gap and water level were considered. The results indicated that both ANFIS and ANN had an acceptable performance in this matter. The best performance of the ANFIS and ANN models had root mean square errors equal to 3.95×10-5 and 4.34×10-5, respectively.