In the field of structural health monitoring (SHM), vibration-based structural damage detection is an important technology to ensure the safety of civil structures. By taking advantage of deep learning, this study introduces a data-driven structural damage detection method that combines deep convolutional neural networks (DCNN) and fast Fourier transform (FFT). In this method, the structural vibration data are fed into FFT method to acquire frequency information reflecting structural conditions. Then, DCNN is utilized to automatically extract damage features from frequency information to identify structural damage conditions. To verify the effectiveness of the proposed method, FFT-DCNN is carried out on a three-story building structure and ASCE benchmark. The experimental result shows that the proposed method achieves high accuracy, compared with classic machine-learning algorithms such as support vector machine (SVM), random forest (RF), K-Nearest Neighbor (KNN), and eXtreme Gradient boosting (xgboost).

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.

In the past few years, structural health monitoring (SHM) has become an important technology to ensure the safety of structures. Structural damage identification methods based on machine learning techniques have gained wide attention due to the advantages of effectively extracting features from monitoring data. However, the existing machine learning-based methods heavily depend on manually selected feature parameters from raw signals. This will cause the selected feature to obtain the optimal solution for a specific condition but may fail to provide a similar performance in other cases. In addition, the feature selection takes a long time, which can fail to achieve real-time performance in a practical structure. To address these problems, this article proposes a hybrid deep learning framework for structural damage identification that includes three components, namely, ensemble empirical mode decomposition (EEMD), Pearson correlation coefficient (PCC), and a convolutional neural network (CNN). The proposed EEMD-PCC-CNN method is capable of automatically extracting features from raw signals to satisfy any damage identification objective. To evaluate the performance of the proposed EEMD-PCC-CNN method, a three-story building structure is investigated. The acceleration signal of the three-story building structure is first analyzed by EEMD. After obtaining the time-frequency information, PCC is utilized to select optimal time-frequency information as the input of the CNN for damage identification. Compared with other classical methods (SVM, KNN, RF, etc.), the experimental results show that the newly proposed EEMD-PCC-CNN method has significant performance advantages in damage identification. In addition, the accuracy of the proposed damage identification method is improved by more than 4% after utilizing EEMD in comparison with CNN alone.

Missing data caused by sensor faults is a common problem in structural health monitoring systems. Due to negative effects, many methods that adopt measured data to infer missing data have been proposed to tackle this problem in previous studies. However, capturing complex correlations from measured data remains a significant challenge. In this study, empirical mode decomposition (EMD) combined with a bidirectional gated recurrent unit (BiGRU) is proposed for the recovery of the measured data. The proposed EMD-BiGRU converts the missing data task as predicted task of time sequence. The core of the method is to predict missing data using the raw data and decomposed subsequence as the decomposed subsequence can improve the predicted accuracy. In addition, the BiGRU in the hybrid model can extract the pre-post correlations of subsequence compared with traditional artificial neural networks. Raw acceleration data collected from a three-story structure are used to evaluate the performance of the EMD-BiGRU for missing data imputation. The recovery results of measure data show that the EMD-BiGRU exhibits excellent performance from two perspectives. First, the decomposed subsequence can improve the accuracy of the BiGRU predicted model. Second, the BiGRU outperforms other machine learning algorithms because it captures more microscopic changes of measured data. The experimental analysis suggests that the change patterns of raw measured signal data are complex, and therefore it is significant to extract the features before modeling.

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).

The static synchronous multi-pressure sensing system (SMPSS) test technique is one of the most conventional techniques used in a wind tunnel. In SMPSS tests, wind pressure sensors are prone to take off leading to missing segment data. This study has predicted single, short-term, and long-term wind pressures by a one-dimensional convolutional neural network based on empirical mode decomposition (EMD-1DCNN). The effectiveness of the EMD-1DCNN model in predicting single, short-term, and long-term wind pressures on bluff bodies has been discussed. It was found that the EMD-1DCNN model had a better performance in predicting single wind pressures compared with the DNN and LSTM models. It was also found that both the DNN and LSTM models failed to predict short-term wind pressures, while the EMD-1DCNN model was effective in addressing this problem. The EMD-1DCNN model extracted the spatial feature between wind pressure sensors and its surrounding sensors to predict long-term wind pressures with high accuracy. The effects of data length used for training the EMD-1DCNN model on the accuracy of prediction were also discussed. It was concluded that 1% datasets (500 samples) were enough for predicting long-term wind pressures with high efficiency. This study has not only presented a way to predict missing data of wind pressures using the EMD-1DCNN model but provided recommendations for the EMD-1DCNN model used for different conditions.