Static strain-based identification of extensive damages in thin-walled structures

Abstract

Interest has been expressed during the past few years toward incorporating structural health monitoring (SHM) systems in ship hull structures for detecting damages that cause significant load-carrying reductions and subsequent load redistributions. The guiding principle of the damage identification strategy considered in this work is based upon measuring, through a limited number of sensors, the static strain redistributions caused by an extensive damage. The problem is tackled as a statistical pattern recognition one, and therefore, methods sourcing from machine learning (ML) are applied. The SHM strategy is both virtually and experimentally applied to a thin-walled prismatic geometry that represents an idealized hull form solely subjected to principal bending stresses (sagging/hogging). Damage modes causing extensive stress redistribution, are abstractly represented by a circular discontinuity. The damage identification problem is treated in a hierarchical order, initialized by damage detection and moving to an increasingly more localized prediction of the damage location. Training datasets for the ML tools are generated from numerical finite element simulations. Measurement uncertainty is propagated in the theoretical strains by information inferred from experimental data. Two different sensor architectures were assessed. An experimental programme is performed for testing the accuracy of the proposed damage identification strategy, yielding promising results and providing valuable insights.