Controlling ground settlement during tunnel excavation in urban areas is a challenging task for contractors even with tight and comprehensive monitoring. In this study, utilizing the settlement monitoring and the sensor data collected during TBM drive, penetration and settlement prediction models are built. We postulated that TBM machine sensors may capture both actions of the machine and the reactions of the ground. Hence the prediction of settlement can be made if an appropriate algorithm is applied. There are a few sequential algorithms such as vanilla LSTM, LSTM with attention, Transformer, and Informer. This paper attempts to identify the optimal algorithm for training sensor data with a sub-workstation equipped in TBM. By comparing the performances of the algorithms, the DALSTM is identified as optimal algorithm for TBM machine data. Furthermore, subsequent analyses are carried out to develop a settlement prediction model, which demonstrates exceptional performance, marking a promising step towards deployment of the proposed method.
The use of TBM in tunnel construction has been gradually increasing in recent years in order to meet high demand for infrastructures such as roads, railways, power supply, telecommunication etc., due to global urbanization. TBM machine has several advantages over the traditional tunneling methods in terms of various safety measures, such as closed mode operation which is applying support pressure on the excavation face with slurry or spoils, and instant support of concrete segment lining, etc., which are mitigating the risk of subsidence.
Numerous research has been conducted on the predictions of the settlement during design phases using analytical, empirical, and numerical methods. One of the most widely accepted analytic solutions is that of Peck (1969), which is based on the measurements from various projects, and modified for the application of TBM excavation for metro projects on mixed geological condition (You and Jung, 2019). However, the design stage predictions have limitations in terms of the uncertainty in construction stages, such as the unforeseen ground condition or inadequacy of construction means and methods.
