No abstract

No abstract

Potential earthquake-induced damage to overlapped tunnels probably occurs during the operation and maintenance of mountain tunnel engineering, especially in the seismically active zone. This study investigated the dynamic response and the failure characteristics of the parallel overlapped tunnel under seismic loadings by employing shaking table tests. The failure mode of the parallel overlapped tunnels was analyzed through macroscopic test phenomena. The dynamic responses of the surrounding rock and tunnel lining were evaluated by acceleration and dynamic strain, respectively. In particular, wavelet packets were used to investigate the spectrum characteristics of the tunnel structure in depth. The failure process of the model can be divided into three stages. The upper-span and the under-crossing tunnels showed different failure characteristics. Additionally, the lining damage on the outer surface of the tunnel mainly occurred on the right side arch waist and the left side wall, whereas the lining damage on the inner surface of the tunnel mainly appeared on the crown and invert. Wavelet packet energy results showed that the energy characteristic distributions of the upper-span and the under-crossing tunnels were not consistent. Specifically, the energy eigenvalues of the crown of the upper-span tunnel and the invert of the under-crossing tunnel were the largest, which should be considered to be the weak parts in the seismic design.

No abstract

Karst is a common engineering environment in the process of tunnel construction, which poses a serious threat to the construction and operation, and the theory on calculating the settlement without the assumption of semi-infinite half-space is lack. Meanwhile, due to the limitation of test conditions or field measurement, the settlement of high-speed railway tunnel in Karst region is difficult to control and predict effectively. In this study, a novel intelligent displacement prediction model, following the machine learning (ML) incorporated with the finite difference method, is developed to evaluate the settlement of the tunnel floor. A back propagation neural network (BPNN) algorithm and a random forest (RF) algorithm are used herein, while the Bayesian regularization is applied to improve the BPNN and the Bayesian optimization is adopted for tuning the hyperparameters of RF. The newly proposed model is employed to predict the settlement of Changqingpo tunnel floor, located in the southeast of Yunnan Guizhou Plateau, China. Numerical simulations have been performed on the Changqingpo tunnel in terms of variety of karst size, and locations. Validations of the numerical simulations have been validated by the field data. A data set of 456 samples based on the numerical results is constructed to evaluate the accuracy of models’ predictions. The correlation coefficients of the optimum BPNN and BR model in testing set are 0.987 and 0.925, respectively, indicating that the proposed BPNN model has more great potential to predict the settlement of tunnels located in karst areas. The case study of Changqingpo tunnel in karst region has demonstrated capability of the intelligent displacement prediction model to well predict the settlement of tunnel floor in Karst region.