The Research and Application of BP Network Tracking Model for Forecasting Oil Well Yield

Based on analyzing fundamental principle of back propagation network model, the paper has established a topology network structure include 12 input layer 25 hidden layer and 2 output layer, 12 input nodes correspond the heighten expression of well performance time cell, 2 output nodes correspond the crude output and water production. According to the tracking model of BP network, this paper takes the learning way of "have teachers", predicted the 37 wellspsila oil production rate and water production rate of PC oil field, the result indicate that the model have better predicted-accuracy, and fitting to predict the oil production rate and water production rate for oil field individual well.