Measuring displacement response is essential in the field of structural health monitoring and seismic engineering. Numerical integration of the acceleration signal is a common measurement method of displacement data. However, due to the circumstances of ground tilt, low-frequency noise caused by instruments, hysteresis of the transducer, etc., it would generate a baseline drift phenomenon in acceleration integration, failing to obtain an actual displacement response. The improved traditional baseline correction methods still have some problems, such as high baseline correction error, poor adaptability, and narrow application scope. This paper proposes a deep neural network model based on empirical mode decomposition (EMD–DNN) to solve baseline correction by removing the drifting trend. The feature of multiple time sequences that EMD obtains is extracted via DNN, achieving the real displacement time history of prediction. In order to verify the effectiveness of the proposed method, two natural waves (EL centro wave, Taft wave) and one Artificial wave are selected to test in a shaking table test. Comparing the traditional methods such as the least squares method, EMD, and DNN method, EMD–DNN has the best baseline correction effect in terms of the evaluation indexes: Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and degree of fit (R-Square).

As special equipment for storing energy, the safety performance of liquified natural gas (LNG) storage tanks under earthquake action is extremely important. To study the dynamic characteristics of the large-scale LNG storage tank structure and the dynamic response under earthquake action, the shaking table test and numerical simulation analysis of the LNG storage tank structure model are carried out. The results of the shaking table test demonstrate that the natural vibration frequency of the tank model is significantly reduced after the isolation measures are taken. The acceleration response of the seismic storage tank increases approximately linearly along the direction of height, and the seismic isolation bearing has a significant seismic isolation effect on the acceleration of the storage tank. The numerical simulation results show that the seismic responses and their spectral characteristic curves of the numerical model and the shaking table test are the same, which verifies the feasibility and rationality of the numerical model. After seismic isolation measures are taken, the seismic responses of large-scale LNG storage tanks, such as base shear force, overturning bending moment and acceleration, are reduced to varying degrees, but the displacement of the storage tank increases to some extent. When carrying out the seismic isolation design of LNG storage tanks, it is necessary to focus on the displacement of the storage tank to prevent damage of the auxiliary pipeline led by excessive displacement.

In order to study the dynamic response of the LNG storage tank under the action of seismic load and the seismic isolation effect of the lead-core rubber bearing, this paper establishes the experimental storage tank model with reference to the structural form of the large-scale LNG storage tank, and the seismic response of the test tank is obtained using a shaking table test. Simplified mechanical models of non-isolated and isolated storage tanks are proposed and the seismic responses of the corresponding storage tanks are calculated using the Newmark-beta method. Under the action of seismic waves with different acceleration peaks, the results show that (a) more excitation directions of the seismic wave can lead to the greater acceleration and displacement response of the tank and (b) the isolation bearing has a damping effect on the acceleration response of the storage tank, but it has an amplifying effect on the displacement of the storage tank. Comparing the results of the simplified model and the shaking table test, it is found that the change trend of the acceleration response of the experimental results and simplified mechanical models is the same. The spectral characteristic curve of them is not large, which verifies the effectiveness of the simplified model.