The serviceability of segmental tunnel linings is attracting more and more attention within the operation of urban rail traffic. Full-scale tests are herein conducted to determine the ultimate bearing capacity of continuously jointed segmental tunnel linings, considering changes of surrounding environment. The design of tested linings and loading schemes are described. The most important results are the evolution of deformations, cracking and opening of joints and forces in bolts. The bearing capacity, role of joint bolts and failure mechanism of the tested linings are analysed. It is found that failure of these linings is caused by the failure of joints. Thus, in order to optimise structural design of tunnel linings, more attention needs to be paid to maximise the joint strength. It is also found that circumferential joint bolts could take action and offer the safety margin in connection with the response of segmental structures. What’s more, a comparison of different experimental loading conditions has shown that segmental lining structures are more vulnerable to lateral unloading than to overload conditions.

In order to develop an effective method to increase the load-bearing capacity of deformed segmental tunnel linings, full-scale tests concerning the ultimate bearing capacity of the linings, strengthened by steel plates, were conducted. The design of the tested linings and the loading scheme are described in this paper. In addition to the bearing capacity, the failure mechanisms of the tested linings were investigated. It was found that bonding of steel plates to the deformed segmental tunnel linings is an effective and practical method for strengthening segmental tunnel linings, thereby enhancing both their ultimate bearing capacity and their overall stiffness. The behaviour of these structures under loading is similar, no matter whether they are strengthened by full-ring or so-called semi-ring steel plates. The failure of the strengthened linings is the consequence of local failure of the bond between the steel plates and the tunnel segment. Therefore, the success of the proposed strengthening method strongly depends on the bonding capacity.

Self-compacting mortar (SCM) has superior workability and long-term durable performance compared to traditional mortar. The strength of SCM, including both its compressive and flexural strengths, is a crucial property that is determined by appropriate curing conditions and mix design parameters. In the context of materials science, predicting the strength of SCM is challenging because of multiple influencing factors. This study employed machine learning techniques to establish SCM strength prediction models. Based on ten different input parameters, the strength of SCM specimens were predicted using two different types of hybrid machine learning (HML) models, namely Extreme Gradient Boosting (XGBoost) and the Random Forest (RF) algorithm. HML models were trained and tested by experimental data from 320 test specimens. In addition, the Bayesian optimization method was utilized to fine tune the hyperparameters of the employed algorithms, and cross-validation was employed to partition the database into multiple folds for a more thorough exploration of the hyperparameter space while providing a more accurate assessment of the model’s predictive power. The results show that both HML models can successfully predict the SCM strength values with high accuracy, and the Bo-XGB model demonstrated higher accuracy (R² = 0.96 for training and R² = 0.91 for testing phases) for predicting flexural strength with low error. In terms of compressive strength prediction, the employed BO-RF model performed very well, with R² = 0.96 for train and R² = 0.88 testing stages with minor errors. Moreover, the SHAP algorithm, permutation importance and leave-one-out importance score were used for sensitivity analysis to explain the prediction process and interpret the governing input variable parameters of the proposed HML models. Finally, the outcomes of this study might be applied to guide the future mix design of SCM specimens.

A new strengthening method employing epoxy-bonded filament wound profiles (FWPs) has been applied to shield tunnels subject to large deformation. Full-scale tests were conducted on the ultimate bearing capacity of linings strengthened by the new method. With consideration for secondary loading, the strengthening measures were applied when the lining deformation reached 120 mm (0.02D). The failure phenomena are described, and the main loading process results were obtained, including load-displacement curves, cracking, and joint openings. The failure mechanisms, the key performance points, and bearing capacities of the tested strengthened linings are discussed and analysed. In addition, a comparison was made between two FWP strengthening methods as well as with epoxy-bonded steel plate strengthening methods. The results show that the epoxy-bonded FWP method is effective and practical for strengthening segmental tunnel linings, which can improve both the ultimate bearing capacity and overall stiffness of the structures. The failure of the strengthened linings is primarily caused by bond failure between the FWPs and the concrete lining segments, indicating that the bonding capacity of the adhesive is of great importance when utilising the proposed strengthening method.