Prediction of Railway Foundation Settlement Based on the BP Neural Network Model

Based on the method of BP neural network,a foundation settlement of BP neural network prediction model was established for a railway subgrade in HeFei area China. In the model, the previous field monitoring data was used as the training sample and the later settlement was predicted. The model was used for four test sections of the railway subgrade. The results showed that for the four test section, the predicted settlement in our model were consistent with the later field monitoring value; At the same time,this model was used to predict the settlement from October 2012 to June 2012 for the four test section, which showed the forecast growth rate of four test section settlement were less than 5%. What is to say, the settlement in October 2012 could be as the final settlement value for the four test sections. I t also showed that the BP neural network prediction model can predict the final settlement of railway foundation commendably,which provided a reliable reference for railway design, construction,operation management and later maintenance.