Research on Modeling Method of Water Displacing Oil Physical Simulation Based on Wavelet Neural Network

Abstract

An actual physical simulation model was constructed to simulate the course of water displacing oil. Under certain physical property conditions, we simulated the water injection well and the oil well on the physical simulation model, and continuous measured online the oil and water content of different area of model in three-dimensional space using the 512 routes resistivity measuring circuit, then we can obtain large numbers of simulation samples. Considering the issues that the relationship between the remaining oil and every parameters of water displacing oil is a complicated and nonlinear, the wavelet neural network was used to establish the water displacing remaining oil model. We adopt a method of reduce the number of the wavelet basic function by analysis the sparsity property of sample data, and use the learning algorithm based on gradient descent to train network. The experimental results show that this method is feasible and effective.