Performance-based structural health monitoring through an innovative hybrid data interpretation framework

The utilization of Structural Health Monitoring (SHM) for performance-based evaluation of structural systems requires the integration of sensing with appropriate data interpretation algorithms to establish an expected performance related to damage or structural change. In this study, a hybrid data interpretation framework is proposed for the long-term performance assessment of structures by integrating two data analysis approaches: parametric (model-based, physics-based) and non-parametric (data-driven, model-free) approaches. The proposed framework employs a network of sensors through which the performance of the structure is evaluated and the corresponding maintenance action can be efficiently taken almost in real-time. The hybrid algorithm proposed can be categorized as a supervised classification algorithm. In the training phase of the algorithm, a Monte-Carlo simulation technique along with Moving Principal Component Analysis (MPCA) and hypothesis testing are employed for simulation, signal processing, and learning the underlying distribution, respectively. The proposed approach is demonstrated and its performance is evaluated through both analytical and experimental studies. The experimental study is performed using a laboratory structure (UCF 4-Span Bridge) instrumented with a Fiber Brag Grating (FBG) system developed in-house for collecting data under common bridge damage scenarios. The proposed hybrid approach holds potential to significantly enhance sensor network design, as well as continuous evaluation of the structural performance.