A Bayesian non-parametric clustering approach for semi-supervised Structural Health Monitoring

A key challenge in Structural Health Monitoring (SHM) is the lack of availability of datafrom a full range of changing operational and damage conditions, with which to train anidentification/classification algorithm. This paper presents a framework based onBayesian non-parametric clustering, in particular Dirichlet Process (DP) mixture models,for performing SHM tasks in a semi-supervised manner, including an online feature extrac-tion method. Previously, methods applied for SHM of structures in operation, such asbridges, have required at least a year’s worth of data before any inferences on performanceor structural condition can be made. The method introduced here avoids the need for train-ing data to be collected before inference can begin and increases in robustness as more dataare added online. The method is demonstrated on two datasets; one from a laboratory test,the other from a full scale test on civil infrastructure. Results show very good classificationaccuracy and the ability to incorporate information online (e.g. regarding environmentalchanges).