Pattern recognition of barely visible impact damage in carbon composites using pulsed thermography

This paper proposes a novel framework to characterise the morphological pattern of Barely Visible Impact Damage using machine learning. Initially, a sequence of image processing methods are introduced to extract the damage contour, which is then described by a Fourier descriptor-based filter. The uncertainty associated with the damage contour under the same impact energy level is then investigated. A variety of geometric features of the contour are extracted to develop an AI model, which effectively groups the tested 100 samples impacted by 5 different impact energy levels with an accuracy of 96%. Predictive polynomial models are finally established to link the impact energy to the three selected features. It is found that the major axis length of the damage has the best prediction performance, with an R2 value up to 0.97. Additionally, impact damage caused by low energy exhibits higher uncertainty than that of high energy, indicating lower predictability.