Prediction Model of Small Faults Extending Length Based on Grey Correlation Analysis and Elman Neural Network

The article elaborates the building, training and simulation method of Elman neural network for predicting the horizontal extending length of small faults in coal seam. Based on grey correlation analysis of the influence factors, we select four predictive parameters including the fault throw, fault strike, fault dip and dip direction. Combined with the typical sample data, we use Matlab software to construct a new network prediction model of small faults extending length prediction, and practical application is given to illuminate the feasibility of the modules.