Reducing the Training Samples for Damage Detection of Existing Buildings through Self-Space Approximation Techniques

Data‐driven methodologies are among the most effective tools for damage detection of complex existing buildings, such as heritage structures. Indeed, the historical evolution and actual behaviour of these assets are often unknown, no physical models are available, and the assessment must be performed only based on the tracking of a set of damage‐sensitive features. Selecting the most representative state indicators to monitor and sampling them with an adequate number of records are therefore essential tasks to guarantee the successful performance of the damage detection strategy. Despite their relevance, these aspects have been frequently taken for granted and little attention has been paid to them by the scientific community working in the field of Structural Health Monitoring. The present paper aims to fill this gap by proposing a multistep strategy to drive the selection of meaningful pairs of correlated features in order to support the damage detection as a one‐class classification problem. Numerical methods to reduce the number of necessary acquisitions and estimate the performance of approximation techniques are also provided. The analyses carried out to test and validate the proposed strategy exploit a dense dataset collected during the long‐term monitoring of an outstanding heritage structure, i.e., the Church of ‘Santa Maria de Belém’ in Lisbon.