Simulation of Reservoir Sediment Flushing of the Three Gorges Reservoir Using an Artificial Neural Network
نویسندگان
چکیده
Reservoir sedimentation and its effect on the environment are the most serious world-wide problems in water resources development and utilization today. As one of the largest water conservancy projects, the Three Gorges Reservoir (TGR) has been controversial since its demonstration period, and sedimentation is the major concern. Due to the complex physical mechanisms of water and sediment transport, this study adopts the Error Back Propagation Training Artificial Neural Network (BP-ANN) to analyze the relationship between the sediment flushing efficiency of the TGR and its influencing factors. The factors are determined by the analysis on 1D unsteady flow and sediment mathematical model, mainly including reservoir inflow, incoming sediment concentration, reservoir water level, and reservoir release. Considering the distinguishing features of reservoir sediment delivery in different seasons, the monthly average data from 2003, when the TGR was put into operation, to 2011 are used to train, validate, and test the BP-ANN model. The results indicate that, although the sample space is quite limited, the whole sediment delivery process can be schematized by the established BP-ANN model, which can be used to help sediment flushing and thus decrease the reservoir sedimentation.
منابع مشابه
Model study reservoir flushing
Sediment flushing of reservoirs is an operational technique, whereby previously accumulated sediments in the reservoirs are hydraulically removed by accelerated flow when the bottom desiltingoutlets of the dam are opened. In this research, the process of sediment flushing is simulated by a three dimensional numerical model in which sediment and flow interaction are reflected in the reservoirs. ...
متن کاملOne dimensional simulation of flushing sediment through reservoirs
Control of sedimentation in reservoirs of dams is considered to be one of the most important issues in exploitation of dams and increasing their useful life. Reservoirs act as traps for sediments and prevent transport of sediments to the river. The deposited sediments will decrease the capacity of the reservoirs so that they cannot be in use any more. Various methods are discussed in this study...
متن کاملBubble Pressure Prediction of Reservoir Fluids using Artificial Neural Network and Support Vector Machine
Bubble point pressure is an important parameter in equilibrium calculations of reservoir fluids and having other applications in reservoir engineering. In this work, an artificial neural network (ANN) and a least square support vector machine (LS-SVM) have been used to predict the bubble point pressure of reservoir fluids. Also, the accuracy of the models have been compared to two-equation stat...
متن کاملIdentifying Flow Units Using an Artificial Neural Network Approach Optimized by the Imperialist Competitive Algorithm
The spatial distribution of petrophysical properties within the reservoirs is one of the most important factors in reservoir characterization. Flow units are the continuous body over a specific reservoir volume within which the geological and petrophysical properties are the same. Accordingly, an accurate prediction of flow units is a major task to achieve a reliable petrophysical description o...
متن کاملArtificial Intelligence for prediction of porosity from Seismic Attributes: Case study in the Persian Gulf
Porosity is one of the key parameters associated with oil reservoirs. Determination of this petrophysical parameter is an essential step in reservoir characterization. Among different linear and nonlinear prediction tools such as multi-regression and polynomial curve fitting, artificial neural network has gained the attention of researchers over the past years. In the present study, two-dimensi...
متن کامل