Dynamic prediction of mechanized shield tunneling performance

Abstract

Slurry pressure balance shield, a kind of tunnel boring machine, is significantly affected by the operation parameters such as advance speed and torque. In this study, a dynamic regulation model is established based on wavelet transform and bidirectional long short-term memory method (Bi-LSTM) to predict advance speed and torque. For comparison, twenty parameters of the shield machine are input to predict the tunneling behavior through the Bi-LSTM model and the LSTM model. Comparison results indicate that the proposed model has a relatively high accuracy. Moreover, parametric sensitivity analysis is made to filter the parameters by using light gradient boosting machine, so that the ranking of importance for all parameters can be gained. The proposed dynamic regulation model is validated by the Sutong gas-insulated transmission line project in China with a complex underwater-work condition, which has a guiding significance in operating and adjusting the shield machine in a dynamic process.