A damage classification approach for structural health monitoring using machine learning

Abstract

Inspection strategies with guided wave-based approaches give to structural health monitoring (SHM) applications several advantages, among them, the possibility of the use of real data fromthe structure which enables continuousmonitoring and online damage identification. These kinds of inspection strategies are based on the fact that these waves can propagate over relatively long distances and are able to interact sensitively with and uniquely with different types of defects. The principal goal for SHM is oriented to the development of efficientmethodologies to process these data and provide results associatedwith the different levels of the damage identification process.As a contribution, thiswork presents a damage detection and classificationmethodology which includes the use of data collected froma structure under different structural states bymeans of a piezoelectric sensor network taking advantage of the use of guided waves, hierarchical nonlinear principal component analysis (h-NLPCA), andmachine learning.The methodology is evaluated and tested in two structures: (i) a carbon fibre reinforced polymer (CFRP) sandwich structure with some damages on the multilayered composite sandwich structure and (ii) a CFRP composite plate. Damages in the structures were intentionally produced to simulate different damage mechanisms, that is, delamination and cracking of the skin.