Tunnel engineering develops rapidly. To study the dynamic response of shield tunnel structure and its bottom soil layer caused by metro train operation, a three-dimensional finite-difference dynamic calculation method is used to establish a shield tunnel-soil layer coupling model based on the shield tunnel project of Maluan Central Station-Jimei Island Station of Xiamen Metro Line 6, and the dynamic response of tunnel structure and its bottom soil layer caused by metro train operation is calculated. The results show that: Under the action of train-induced vibration, the shield tunnel structure mainly bears compressive stress and generates compressive deformation. The dynamic response of tunnel structure represents a significant increasing trend with the enhancement of train-induced vibration load. Under the same load strength, dynamic response change amplitude of structure is not obvious with tunnel structural stiffness, stress is gradually increasing, and displacement is weakening. The deeper the soil depth at the bottom of the shield tunnel structure, the weaker the dynamic response of the soil layer. The stress response of the soil layer at the same depth is increasing with the train-induced vibration load improving, but the displacement response has a stage characteristic. The dynamic response of the soil layer at the same depth does not change obviously with the increase in shield tunnel structural stiffness, but the stress response gradually increases, and the displacement response becomes weak. In general, investigation of the dynamic response of the subway shield tunnel under train-induced vibration has important practical significance for maintaining the long-term safe operation of subway tunnels.

With the rapid development of long or extra‐long highway tunnel, accurate and reliable methods and techniques to forecast traffic flow for road tunnel are urgently needed to improve the ventilation efficiency and saving energy. This paper presents a new hybrid Gaussian process regression (GPR) optimized by particle swarm optimization (PSO) for coping with the forecasting of the uncertain, nonlinear, and complex traffic flow for road tunnel. In this proposed coupling approach, the PSO algorithm is employed to overcome the disadvantages of too strong dependence of optimization effect on initial value and easy falling into local optimum of the traditional conjugate gradient algorithm and accurately search the optimal hyperparameters of the GPR method, and the GPR model simulates the internal uncertainties and dynamic feature of tunnel traffic flow. The predicted results indicate that the proposed PSO‐GPR algorithm with different kernel function is able to predict traffic flow for road tunnel with a higher degree of accuracy. The PSO‐GPR‐CK is effective in boosting the forecasting accuracy in comparison with the single kernel function and is worth promoting in the field of traffic flow forecasting for road tunnel to improve the ventilation efficiency.