.png){kind=icon}
Return
A real-time anomaly detection method for movable structures based on Bayesian dynamic linear model
.png){kind=icon}
PRE
AI
DOI：10.1007/s13349-026-01084-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Structural anomaly detection based on monitoring data plays a crucial role in ensuring the safe operation of civil engineering structures. As a type of data-driven approach, time series methods have been widely applied in structural anomaly detection, where damage-sensitive features can be directly extracted from the time series data without physical models of structures. In this study, a real-time anomaly detection method based on the Bayesian Dynamic Linear Model (BDLM) is proposed for structural anomaly identification of a movable structures. To better account for the motion state of movable structures, an improved classificatory regression BDLM is proposed. On this basis, the Bayesian factor is introduced to identify structural anomalies. In addition, the Mahalanobis distance is used to assess abnormal states, so that the structural anomalies and accidental anomalies of individual data points can be distinguished. Furthermore, a self-feedback mechanism is introduced to improve the efficiency of model updating after the emergence of abnormal data. Finally, the effectiveness of the present BDLM was verified by applying it to the anomaly detection of a rotating grandstand structure using numerically simulated and real monitored stress data.
Keywords:
Bayesian dynamic linear model
Real-time anomaly detection
Movable structures
Mahalanobis distance
Journal
IF:
4.3
Papers:
914
Citations:
2.9K
Organization
Cited Papers
Probabilistic damage localization by empirical data analysis and symmetric information measure.png)
MEASUREMENT
MEASUREMENTIF5.6
PREAI
ShareSaveBayesian damage identification based on autoregressive model and MH-PSO hybrid MCMC sampling method
PREAI
ShareSaveShareSaveShareSaveStructural Damage Detection of Cable-Stayed Bridges Using Changes in Cable Forces and Model Updating
PREAI
ShareSaveBayesian forecasting of multivariate time series: scalability, structure uncertainty and decisions
PREAI
ShareSave
View more