Description
In recent years an increasing attention has been given to the application of Artificial Intelligence techniques within the context of Structural Health Monitoring (SHM) of Civil Engineering structures. Multiple advantages compared to traditional OMA-based techniques are achieved, such as a relatively low computational efforts and a possible insensitivity to environmental and operational variability (EOV). The present paper proposes an Auto-Encoder-based approach to automatically handle EOVs and, at the same time, to detect structural changes. The proposed procedure is based on the adoption of an Auto-Encoder (AE) model to reconstruct the multivariate measurement data collected during continuous dynamic monitoring. In more details, an AE model is trained with data collected simultaneously from all the available channels during a reference period, in which the structure is supposed to be in healthy condition under normal EOVs. Through the training procedure, the internal bottleneck layer of AE is supposed to learn how the variation of measured data is affected by the normal EOV. Subsequently, the trained AE is used to reconstruct the data collected from unknown scenario, providing a mean reconstruction error (between the measured and the reconstructed signals) that increases as soon as the monitored system changes from its healthy condition. The application of the AE-based procedure is exemplified to the benchmark KW51 bridge (a steel bowstring railway bridge in Leuven, Belgium), showing that the AE model, trained simultaneously with all the available sensors, is capable of detecting the structural changes due to a retrofitting performed on the bridge, under changing environmental and operational conditions.
