City Research Online

Abstract

The development of Tunnel Boring Machines (TBMs) has improved the efficiency of tunnelling; however, uncertainty in ground response complicates the anticipation of potential risks. Therefore, an accurate prediction of ground movements also known as settlement is essential for effective mitigation before and during construction. Conventional prediction methods are often constrained by site specificity, computational demands, and simplified geological representation, which has driven the adoption of Machine Learning (ML) approaches. This study analyses monitoring data from the HS2 Project to investigate the relationship between surface settlement and TBM parameters to identify the key variables, forming a preliminary step towards a Machine Learning-based predictive framework.

Publication Type:	Conference or Workshop Item (Paper)
Subjects:	T Technology > TA Engineering (General). Civil engineering (General)
Departments:	School of Science & Technology School of Science & Technology > Department of Engineering
SWORD Depositor:	Symplectic Administrator

Export

Downloads