A Brief Introduction to Recent Developments in Population-Based Structural Health Monitoring

• Published in: Frontiers in built environment Vol. 6
• Main Authors: Worden, Keith, Bull, Lawrence A., Gardner, Paul, Gosliga, Julian, Rogers, Timothy J., Cross, Elizabeth J., Papatheou, Evangelos, Lin, Weijiang, Dervilis, Nikolaos
• Format: Journal Article
• Language: English
• Published: Frontiers Media S.A 09-09-2020
• Subjects: complex networks; graph theory; machine learning; population-based structural health monitoring (PBSHM); semi-supervised learning; transfer learning
• ISSN: 2297-3362; 2297-3362
• DOI: 10.3389/fbuil.2020.00146

One of the main problems in data-based Structural Health Monitoring (SHM), is the scarcity of measured data corresponding to damage states in the structures of interest. One approach to solving this problem is to develop methods of transferring health inferences and information between structures in an identified population—Population-based SHM (PBSHM). In the case of homogenous populations (sets of nominally-identical structures, like in a wind farm), the idea of the form has been proposed which encodes information about the ideal or typical structure together with information about variations across the population. In the case of sets of disparate structures—heterogeneous populations—transfer learning appears to be a powerful tool for sharing inferences, and is also applicable in the homogenous case. In order to assess the likelihood of transference being meaningful, it has proved useful to develop an abstract representation framework for spaces of structures, so that similarities between structures can formally be assessed; this framework exploits tools from graph theory. The current paper discusses all of these very recent developments and provides illustrative examples.