The Analysis of Wavelet Neural Network in Oilfield Production Prediction
Lijun Wang, Su Bei Zhang, Qiang Guo Duan · Applied Mechanics and Materials · 2013
The production forecast is a basic premise in the design of the oil exploration program. Accurate production predictions can provide guidance on the direction of oilfields exploration program adjustments and be able to determine the scale of mining of the oilfields. Because of the varying nature of geological reservoirs, oil field production forecast error is large. Because wavelet neural network is better features of convergence and dealing with complex geological conditions, so it can provide a more accurate prediction than the conventional prediction to heterogeneous reservoir. After the actual reference data are simulated, calculation error is very small, and to prove its production forecast can be used as the reference of the real reservoir exploitation.