Tunnel Settlement Prediction by Transfer Learning

Abstract

Tunnel settlement has a significant impact on property security and personal safety. Accurate tunnel-settlement predictions can quickly reveal problems that may be addressed to prevent accidents. However, each acquisition point in the tunnel is only monitored once daily for around two months. This paper presents a new method for predicting tunnel settlement via transfer learning. First, a source model is constructed and trained by deep learning, then parameter transfer is used to transfer the knowledge gained from the source model to the target model, which has a small dataset. Based on this, the training complexity and training time of the target model can be reduced. The proposed method was tested to predict tunnel settlement in the tunnel of Shanghai metro line 13 at Jinshajiang Road and proven to be effective. Artificial neural network and support vector machines were also tested for comparison. The results showed that the transfer-learning method provided the most accurate tunnel-settlement prediction.