Research On The Prediction Of Remaining Oil Parameters Based On Neural Networks

The study on the prediction of remaining oil parameters after the first and two oil production in China has not only considerable economic effect,but also the safety of the national oil strategy.It is of great theoretical significance and practical value to explore the efficient and reliable information processing methods for the prediction of remaining oil parameters.In the research of oil,residual oil research plays a very important role.In this paper,the BP neural network algorithm is used to establish an effective neural network model,and the prediction of porosity and permeability parameters of remaining oil is studied.Firstly,according to the actual field data for data preprocessing,and determine the discussion method mainly includes the data normalization method;then using BP neural network method,MATLAB software is used to simulate and analysis programming.The use of a practical oil production data as input data,between the reservoir depth and porosity and permeability parameters to establish a nonlinear mapping relations,so as to predict the reservoir parameters in this area within the scope of.The simulation results show that the proposed method is effective and accurate.