Excavation of a superlarge diameter tunnel by tunnel boring machine (TBM) is different from that of a shield tunnel with normal dimension, in which the control system of the superlarge TBM is very complicated and difficult to operate. Hence, it is very important to focus on the control and management of significant parameters to ensure excavation stability under uncertainty. In this paper, we (i) utilize a BIM‐based big data platform (BIM‐BDP) to manage the essential construction data of tunnel project in digital format; (ii) adopt the global sensitivity analysis (SA) to recognize significant parameters for shield excavation based on polynomial chaos expansion (PCE)–extended Fourier amplitude sensitivity test (eFAST) model; and (iii) employ the uncertainty analysis (UA) to discover the correlation between significant parameters from the data of the BIM‐BDP. This research contributes to (i) the body of knowledge of proposing a more appropriate research methodology that can cope with aleatory and epistemic uncertainty and support uncertainty and sensitivity analysis (UA/SA) processes based on data from BIM‐BDP and (ii) the state of practice by providing a data‐driven surrogate model to simulate system behaviors of shield excavation with high reliability and to reduce dependency on domain experts. Here, we pay close attention to the most influential parameters that require priority parameter control, which can help administrators optimize the management of shield parameters during tunnel excavation.

During the construction of a shield tunnel, it will disturb the surrounding ground and affect the use and structural safety of buildings around the tunnel. The geometric parameters of the tunnel, the operating parameters of the shield machine, and the geological parameters will affect the degree of disturbance. However, the existing theories and models are difficult to comprehensively consider the interaction of these factors, and it is difficult to accurately predict the response of the formation to solve the above problems. The research is based on the machine learning algorithm to establish a prediction model of stratum settlement caused by shield tunneling, which provides a new idea for real time prediction of the ground response caused by shield tunneling and risk reduction. The main results of this research are as follows: (1) propose a novel quantification method for geological parameters that can comprehensively consider the physical and mechanical properties of the rock,soil layers, and the geometric characteristics of depth and thickness and (2) establish a more robust proxy model and use the k‐fold cross‐validation method to enhance its performance.

This study deals with the variation in strength of clays stabilized by a special binder—the CEM II/B‐V type of Portland‐fly ash cement. Two sources of uncertainties were examined, that is, the uncertainty in cement fraction in the binder, and the nonuniformity in binder concentration resulted from the process of mixing binder slurry with in situ clays. These two uncertainties were quantitatively described as two random variables, and the analyses were conducted through the Monte Carlo simulation method. Results indicate that the strength is insensitive to the cement fraction in the binder but is sensitive to the binder concentration; the variation of the latter even results in an amplified variation of strength. The variation of binder concentration is proposed to be linked up with the variation of strength through the operational parameter of blade rotation number. By doing so, the results could benefit designers in quality control prior to the construction of soil stabilization.