Prediction of Mining Ground Settlement Based on BP Neural Network
Cheng Sh · Geomatics & Spatial Information Technology · 2015
BP neural network has very strong nonlinear mapping ability,wide reaction for classification and recognition,approximation,regression,compression and other fields. In this paper,the theoretical basis based on BP neural network,the use of a mining area subsidence observation point 1-10 period of the settlement data,combined with MATLAB for establishing prediction model of surface subsidence in mine,and to predict the 11-15 period of settlement. The predicted values were compared with the measured values,the analysis of the accuracy of the prediction model,the results show that the BP neural network is used to study the surface subsidence in mining area is feasible.