Production Forecast of Coalbed Methane Based on GA Optimized BP Neural Network

Abstract

Reliable and scientific prediction of the productivity of coalbed methane wells will certainly provide some convenience for the mining of coalbed methane, thus improving the drainage efficiency of coalbed methane to some extent. Based on the characteristics of coalbed methane drainage data, this paper constructs a prediction model based on deep belief network and applies it to the prediction of coalbed methane production capacity. Compared with the traditional BP neural network, this model avoids the traditional BP neural network model training. In the process, it is easy to fall into the optimal value and the gradient dispersion occurs as the number of hidden layers increases, and the prediction accuracy is improved to some extent. Finally, combined with the example verification, and compared with the BP method. The prediction results show that the proposed GA-BP optimization model has higher prediction accuracy in the production capacity prediction of coalbed methane wells.