Slope Displacement Prediction Model Based on LMD and BP Neural Network

Slope displacement time series prediction model,a combination of Local mean decomposition(LMD) and BP neural network is presented.By selecting train samples on the basis of monitoring data on slope displacement and conducting an adaptive decomposing, several production function is obtained.After that, BP neural network is used to forecast the PF and finally adding it all up and the result is the predicton of slope displacement. BP neural network is used to optimize the parameters so as to improve the forecast accuracy.The model is put into application on the slope displacement forecasting of the permanent lock slope.The case study shows that the prediction result is of high accuracy, scientifically valid and has potential value in the field of slope displacement time series prediction.