Computational methods for wireless structural health monitoring of cultural heritages

Michael Bertolli (1) , Massimo Donelli (1) , Andrea Massa (2, 1) , Giacomo Oliveri (1) , Alesandro Polo (1) , Fabrizio Robol (1) , Lorenzo Poli (1) , Angelo Gelmini (1) , Giorgio Gottardi (1) , Abdul Mohammad Hannan (1) , Bui Phuoc Le Trong (1) , Paolo Rocca (1) , Claudio Sacchi (1) , Federico Viani (1) , Toshifumi Moriyama , Takashi Takenaka (3) , Marco Salucci (1)

1 UNITN - Università degli Studi di Trento = University of Trento
2 L2S - Laboratoire des signaux et systèmes
3 Nagasaki University

The structural health monitoring of cultural heritages is addressed in this paper. The arising inverse problem is solved through the Learning-by-Examples (LBE) paradigm, exploiting data collected by a Wireless Sensor Network (WSN). More in detail, low-cost and low-size sensing devices are spread over the scenario to be monitored, allowing environmental data as well as acceleration and vibration information to be acquired and processed by means of a Support Vector Machine (SVM) in order to detect the presence/absence of a damage in the monitored structure. The proposed approach has been preliminary validated in a laboratory controlled environment, demonstrating promising performance.

Domaines: Electromagnétisme; Traitement du signal et de l'image [eess.SP]

Michael Bertolli, Massimo Donelli, Andrea Massa, Giacomo Oliveri, Alesandro Polo, et al.. Computational methods for wireless structural health monitoring of cultural heritages. Journal of Physics: Conference Series, 2018, 1131, pp.1-7. ⟨10.1088/1742-6596/1131/1/012005⟩. ⟨hal-01962630⟩