Anomaly detection of structural health monitoring data using the maximum likelihood estimation-based Bayesian dynamic linear model

Abstract

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.

Application of PZT Ceramic Sensors for Composite Structure Monitoring Using Harmonic Excitation Signals and Bayesian Classification Approach

“…In the paper a framework for data classification based on Bayesian inference is proposed. Bayesian approach, due to its generality and flexibility, is often adopted for data classification in the SHM field [62][63][64][65][66].…”

Bayesian dynamic regression for reconstructing missing data in structural health monitoring

“…Given the observations Y t , stack the vectors to form a block Hankel matrix. Suppose D is a Hankel matrix with the form 47,48 The subspace method calculates parameters to generate the estimation of the latent state through singular value decomposition (SVD). The input D is obtained by with the estimation given by where U and S have the orthonormal columns; d denotes the dimension of latent variables; normalθ ^ s is denoted as the extended observability matrix and represents the state estimation; and normalΣ H contains the singular values.…”

Photogrammetric Process to Monitor Stress Fields Inside Structural Systems

“…The use of combined spatial and temporal filters smooths the measurements and attempts to eliminate camera and image classification errors such as outliers. It is important to highlight, however, that other techniques could also be applied to remove anomalies, such as, for instance, the maximum likelihood estimation (MLE) [67,68].…”