The BP Network Study of the Time Series Overrolling Model for Forecasting the Oilfield Output

Based on analyzing fundamental principle of Back Propagation Network Model, in view of the limitations of BP algorithm, this paper proposed the homologous improved-algorithm from the two aspects of quickening the BP learning speed and raising the degree of convergence. In the course of the complex water flood development, the paper, considering the adaptability feature of the different random factors affecting the wells yield, built the BP time series overrolling model for forecasting the oilfield output, and predicted the wells output using the model, the result indicate that the model have better predicted-accuracy, and fitting to predict the oil production rate and water production rate for different development phase.