Research on the prediction of foundation settlement by BP neural network

Abstract

To accurately predict the change of foundation settlement after surcharge preloading treatment, taking the surcharge preloading engineering area of an airport as an example, a foundation settlement prediction model based on BP neural network is constructed. Using two sets of field measured settlement data as the data basis, the model is trained and predicted, and its prediction performance is evaluated. The research results show that BP neural network has good performance in predicting foundation settlement, with a prediction accuracy of more than 98%. It is a relatively ideal prediction method. The research results can provide theoretical support for settlement prediction after foundation treatment.