Abstract
Prediction of the maximum surface settlement due to shallow tunnelling in soft grounds is a valuable metrics in ensuring safe operations, particularly in urban areas. Although numerous researches have been devoted to this issue, due to the complexity and a large number of the effective parameters, no comprehensive solution to the problem is available. In this study, a shallow tunnel classification system (STCS), based on maximum settlement, is proposed. The STCS holds on the results of several tunnelling projects around the world. The classifier categorises a tunnel based on geometry, ground, and performance characteristics. A decision tree classification method, after training with 20 cases, was successful to predict the maximum settlement for 14 tunnelling projects. The maximum surface settlement predictions were in the form of assigning a class label to each tunnel. Four tunnel classes were defined as follow: (i) class A (maximum settlement<9.9mm), (ii) class “B” (10⩽maximum settlement<19.9mm), (iii) class “C” (20⩽maximum settlement<29.9mm), and (iv) class “D” (maximum settlement⩾30mm). The most explanatory independent variables were selected, by the STCS, as follow: tunnel depth, diameter, volume loss, and normalised volume loss. The proposed classification scheme can be employed as a decision making aid in settlement prediction/prevention in shallow tunnelling in soft grounds. The STCS is proposed as a supplemental tool to the observational methods, and it is not expected to be a stand-alone measure for settlement.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.