Time history testing using a shaking table is one of the most widely used methods for assessing the dynamic response of structures. In shaking-table experiments and on-site monitoring, acceleration sensors are facing problems of missing data due to the fact of measurement point failures, affecting the validity and accuracy of assessing the structural dynamic response. The original measured signals are decomposed by ensemble empirical mode decomposition (EEMD), and the widely used deep neural networks (DNNs), gated recurrent units (GRUs), and long short-term memory networks (LSTMs) are used to predict the subseries of the decomposed original measured signal data to help model and recover the irregular, periodic variations in the measured signal data. The raw acceleration data of a liquefied natural gas (LNG) storage tank in shaking-table experiments were used as an example to compare and discuss the method’s performance for the complementation of missing measured signal data. The results of the measured signal data recovery showed that the hybrid method (EEMD based) proposed in this paper had a higher complementary performance compared with the traditional deep learning methods, while the EEMD-LSTM exhibited the best missing data complementary accuracy among all models. In addition, the effect of the number of prediction steps on the prediction accuracy of the EEMD-LSTM model is also discussed. This study not only provides a method to fuse EEMD and deep learning models to predict measured signal’ missing data but also provides suggestions for the use of EEMD-LSTM models under different conditions.

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).