LASER shock delamination generation and machine learning-based damage quantification in CFRP composites plates

Abstract

In the aeronautic industry, composite materials are becoming more widespread due to their high strength to mass ratio. Piezoelectric elements can be permanently incorporated on composite parts during the manufacturing process and can then be used to provide a diagnosis of their current health and the prognosis of their remaining operational life. This approach is called Structural Health Monitoring (SHM). In this work, we approach delamination quantification in Carbon Fiber Reinforced Polymer (CFRP) plates as a classification problem whereby each class corresponds to a certain damage extent. Starting from the assumption that damage causes a structure to exhibit nonlinear response, we investigate whether the use of Nonlinear Model Based Features (NMBF) increases classification performance. NMBF are computed based on parallel Hammerstein models which are identified with an Exponential Sine Sweep (ESS) signal. Delamination damage is introduced into samples in a calibrated and realistic way using LASER Shock Wave Technique (LSWT) and more particularly symmetrical LASER shock configuration. Obtained results demonstrate that the proposed approach is very reliable for delamination quantification.