Damage Detection In Concrete Beams Strengthened With Frp Using Principal Component Analysis And K-Means Clustering

Fiber reinforced polymers (FRP) strengthening systems have been considered as an effective technique to retrofit concrete structures and their use nowadays is more and more extended. However, one of their main disadvantages is a possible brittle failure mode provided by a sudden debonding of the FRP. Digital image correlation (DIC) has been used in the past for the detection of abnormalities from surface digital images. In this work, an efficient computer-aided diagnosis (CAD) system for damage identification at its earliest stages for this type of FRP strengthening is developed. For it, a clustering classifier is implemented from the cells of the strain maps built with a DIC system. Additionally, to optimize the procedure, principal component analysis (PCA) is used for feature selection.