A hybrid Structural Health Monitoring approach based on reduced-order modelling and deep learning

Luca Rosafalco, Alberto Corigliano, Andrea Manzoni, Stefano Mariani
2019 Proceedings of 6th International Electronic Conference on Sensors and Applications   unpublished
Recent advances in sensor technologies coupled with the development of machine/deep learning strategies are opening new frontiers in Structural Health Monitoring (SHM). Dealing with structural vibrations recorded with pervasive sensor networks, SHM aims at extracting meaningful damage-sensitive features from the data, shaped as multivariate time series, and taking real-time decisions concerning the safety level. Within this context, we discuss an approach able to detect and localize a
more » ... ocalize a structural damage avoiding any pre-processing of the acquired data. The method takes advantage of the capability of Deep Learning of Fully Convolutional Networks, trained during an offline SHM phase. As a hybrid model-and data-based solution is looked for, Reduced Order Models are also built in the offline phase to reduce the computational burden of the whole monitoring approach. Through a numerical benchmark test, we show how the proposed method can recognize and localize different damage states.
doi:10.3390/ecsa-6-06585 fatcat:vfkvyicwcrcfblsrjheitw7cpi