Damage detection is one of the most important tasks for structural health monitoring of civil infrastructure. Before a damage detection algorithm can be applied, the integrity of the data must be ensured; otherwise results may be misleading or incorrect. Indeed, sensor system malfunction, which results in anomalous data (often called faulty data), is a serious problem, as the sensors usually must operate in extremely harsh environments. Identifying and eliminating anomalies in the data is crucial to ensuring that reliable monitoring results can be achieved. Because of the vast amounts of data typically collected by a structural health monitoring system, manual removal of the anomalous data is prohibitive. Machine learning methods have the potential to automate the process of data anomaly detection. Although supervised methods have been proven to be effective for detecting data anomalies, two unresolved challenges reduce the accuracy of anomaly detection: (1) the class imbalance and (2) incompleteness of anomalous patterns of training dataset. Unsupervised methods have the potential to address these challenges, but improvements are required to deal with vast amounts of monitoring data. In this article, the generative adversarial networks are combined with a widely applied unsupervised method, that is, autoencoders, to improve the performance of existing unsupervised learning methods. In addition, the time-series data are transformed to Gramian Angular Field images so that advanced computer vision methods can be included in the network. Two structural health monitoring datasets from a full-scale bridge, including examples of anomalous data caused by sensor system malfunctions, are utilized to validate the proposed methodology. Results show that the proposed methodology can successfully identify data anomalies with good accuracy and robustness, hence can overcome one of the key difficulties in achieving automated structural health monitoring.

Massive data that provide valuable information regarding the structural behavior are continuously collected by the structural health monitoring (SHM) system. The quality of monitoring data is directly related to the accuracy of the structural condition assessment and maintenance decisions. Data missing is a common and challenging issue in SHM, compromising the reliability of data-driven methods. Thus, the accurate reconstruction of missing SHM data is an essential step for the reliable evaluation of the structural condition. Data recovery can be considered as a regression task by modeling the correlation among sensors. The Bayesian linear regression (BLR) model has been extensively used in probabilistic regression analysis due to its efficiency and the ability of uncertainty quantification. However, because of the fixed coefficients (refer to a static model) and linear assumption, the BLR model fails to accurately capture the relationship and accommodate the changes in related variables. Given this limitation, this study presents a Bayesian dynamic regression (BDR) method to reconstruct the missing SHM data. The BDR model assumes that the linear form is only locally suitable, and the regression variable varies according to a random walk. In particular, the multivariate BDR model can reconstruct the missing data of different sensors simultaneously. The Kalman filter and expectation maximum (EM) algorithms are employed to estimate the state variables (regressors) and parameters. The feasibility of the multivariate BDR model is demonstrated by utilizing the data from a building model and a long-span cable-stayed bridge. The results show that the multivariate BDR model exhibits excellent performance to rebuild the missing data in terms of both computational efficiency and accuracy. Compared to the standard BLR and linear BDR models, the quadratic BDR model owns better reconstruction accuracy.

Enormous data are continuously collected by the structural health monitoring system of civil infrastructures. The structural health monitoring data inevitably involve anomalies caused by sensors, transmission errors, or abnormal structural behaviors. It is important to identify the anomalies and find their origin (e.g. sensor fault or structural damage) to make correct interventions. Moreover, online anomaly identification of the structural health monitoring data is critical for timely structural condition assessment and decision-making. This study proposes an online approach for detecting anomalies of the structural health monitoring data based on the Bayesian dynamic linear model. In particular, Bayesian dynamic linear model, consisting of various components, is implemented to characterize the feature of real-time measurements. Expectation maximization algorithm and Kalman smoother are combined to estimate the Bayesian dynamic linear model parameters and generate log-likelihood functions. The subspace identification method is introduced to overcome the initialization issue of the expectation maximization algorithm. The log-likelihood difference of consecutive time steps is then used to determine thresholds without introducing extra anomaly detectors. The proposed Bayesian dynamic linear model-based approach is first illustrated by the simulation data and then applied to the structural health monitoring data collected from two long-span bridges. The results indicate that the proposed method exhibits good accuracy and high computational efficiency and also allows for reconstructing the strain measurements to replace anomalies.