Back Analysis of Surrounding Rock Parameters in Pingdingshan Mine Based on BP Neural Network Integrated Mind Evolutionary Algorithm

The mechanical parameters of surrounding rock are an essential basis for roadway excavation and support design. Aiming at the difficulty in obtaining large experimental errors, optimized BP neural network model is proposed this paper. mind evolutionary algorithm can adequately search optimal initial weights thresholds, while has advantage strong nonlinear prediction ability. So, (MEA-BP model) takes two models. It not only avoid local extreme value problem but also improve accuracy reliability results. Based on orthogonal test method finite element analysis method, training samples established. relationship between deformation established by MEA-BP model, respectively. importance three input variables shows that ?D most important variable, ?BC smallest impact. comparison performance demonstrates thresholds value. Finally, been well applied to predicting parameter Pingdingshan mine area, which proves model.