Spatio-temporal feature fusion for real-time prediction of TBM operating parameters: A deep learning approach

Xianlei Fu, Limao Zhang

    School of Civil and Environmental Engineering, Nanyang Technological University, 50 Nanyang Avenue, 639798, Singapore

Highlights

• A spatio-temporal prediction approach to estimate TBM performance is proposed.
• Long short-term memory based deep learning model is used to perform real-time forecasting.
• Global sensitivity analysis is performed to quantify the contribution of variables.
• A realistic tunnel case in Singapore is used to demonstrate the applicability and effectiveness.
• It can achieve a high accuracy with an MAE of 1.261 mm and an RMSE of 1.955 mm.

https://www.sciencedirect.com/science/article/abs/pii/S0926580521003885