Smart Structures and Systems, Vol. 6, No. 3 (2010) 000-000 1 Vibration-based structural health monitoring using large sensor networks A. Deraemaeker 1 , A. Preumont 1 , E. Reynders 2 , G. De Roeck 2 , J. Kullaa 3 , V. Lamsa 3 , K. Worden 4 * , G. Manson 4 , R. Barthorpe 4 , E. Papatheou 4 , P. Kudela 5 , P. Malinowski 5 , W. Ostachowicz 5 , and T. Wandowski 5 ULB, Active Structures Laboratory, avenue F.D.Roosevelt, 50, B-1050 Brussels, Belgium KUL, Department of Civil Engineering, Kasteelpark Arenberg 40, B-3001 Heverlee (Leuven), Belgium Aalto University School of Science and Technology, P.O.Box 11000, FI-00076 AALTO, FINLAND Department of Mechanical Engineering, University of Sheffield, Mappin St, Sheffield S1 3JD, UK IFFM, Polish Academy of Science, Poland (Received 26 September 2008, Accepted 1 August 2009) Abstract. Recent advances in hardware and instrumentation technology have allowed the possibility of deploying very large sensor arrays on structures. Exploiting the huge amount of data that can result in order to perform vibration-based structural health monitoring (SHM) is not a trivial task and requires research into a number of specific problems. In terms of pressing problems of interest, this paper discusses: the design and optimisation of appropriate sensor networks, efficient data reduction techniques, efficient and automated feature extraction methods, reliable methods to deal with environmental and operational variability, efficient training of machine learning techniques and multi-scale approaches for dealing with very local damage. The paper is a result of the ESF-S3T Eurocores project “Smart Sensing For Structural Health Monitoring” (S3HM) in which a consortium of academic partners from across Europe are attempting to address issues in the design of automated vibration-based SHM systems for structures. Keywords: structural health monitoring (SHM); vibration-based methods; sensor networks; machine learning; lamb waves. 1. Introduction Optimal maintenance of civil engineering infrastructure will require a precise knowledge of its actual state of integrity and possible remaining lifetime. For many years, researchers have worked on global monitoring methods based on the analysis of the vibration signals of structures (Salawu 1997, Doebling et al. 1998, Alvandi and Cremona 2006, Montalvao et al. 2006), as an alternative to traditional, local monitoring techniques based on Non-Destructive Testing (NDT) inspection (Grandt 2003). Although a large body of the literature is devoted to the subject of vibration-based damage identification methods, industrial application of fully automated Structural Health Monitoring (SHM) systems are quite rare and usually confined to aerospace structures; the status of these systems is often “under development”. Although the development of SHM has been concentrated around aerospace structures, there is a marked interest in transferring the technology into civil engineering. This transfer is anticipated to *Corresponding Author, Professor, E-mail: k.worden@sheffield.ac.uk