Research on ACO-BP Based Prediction Method of The Oilfield Production Stimulation Results

Abstract

In the process of oilfield development, production stimulation is important to stabilize the oilfield production output. In order to accurately predict the results of stimulation, and reasonably plan the stimulation actions for the oilfield, this paper proposes a prediction model that uses the ant colony algorithm ACO to optimize the back propagation neural network (BP neural network). Using Matlab to conduct ACO-BP oil field stimulation results prediction model tests, the experimental results show that the model is effective in predicting oilfield stimulation outcome; and the prediction accuracy and stability of the model are better than those of BP and FA-BP network prediction models.