A Bayesian state-space approach for damage detection and classification. (November 2017)

• Record Type: Journal Article
• Authors: Dzunic, Zoran; Chen, Justin G.; Mobahi, Hossein; Büyüköztürk, Oral; Fisher, John W.
• Is Part Of: Mechanical systems and signal processing. Volume 96(2017)
• Page Start: 239
• Page End: 259
• Publication Date: 2017-11
• Subjects: Graphical models -- Bayesian inference -- Structural health monitoring -- State-space model -- Damage detection; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2017.03.043
• Languages: English
• ISSNs: 0888-3270

Abstract

Highlights: A switching Bayesian model for dependency analysis is proposed for damage detection. The model infers the statistical temporal dependency between measurement locations. Probabilistic estimates of the occurrence of damage are obtained from the model. The methodology is demonstrated with experimental data from a real world structure. Abstract: The problem of automatic damage detection in civil structures is complex and requires a system that can interpret collected sensor data into meaningful information. We apply our recently developed switching Bayesian model for dependency analysis to the problems of damage detection and classification. The model relies on a state-space approach that accounts for noisy measurement processes and missing data, which also infers the statistical temporal dependency between measurement locations signifying the potential flow of information within the structure. A Gibbs sampling algorithm is used to simultaneously infer the latent states, parameters of the state dynamics, the dependence graph, and any changes in behavior. By employing a fully Bayesian approach, we are able to characterize uncertainty in these variables via their posterior distribution and provide probabilistic estimates of the occurrence of damage or a specific damage scenario. We also implement a single class classification method which is more realistic for most real world situations where training data for a damaged structure is not available. We demonstrate the methodology with experimental test data from a laboratory model structure and accelerometer data from a real world structure during different environmental and excitation conditions.