Abstract
This article proposes a novel framework to characterize the morphological pattern of barely visible impact damage using machine learning. Initially, a sequence of image processing methods is 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 artificial intelligence 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 R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> value up to 0.97. Additionally, impact damage caused by low energy exhibits higher uncertainty than that of high energy, indicating lower predictability.
Highlights
Due to its excellent material properties such as low density, high strength, corrosion resistance, and high-freedom design characteristics, composite materials play an increasingly essential role in the field of automotive [1] and aviation industries [2]
A CFRP impact damage inspection method was proposed by Zhang et al [10] based on manifold learning using ultrasonic induced thermography for Barely Visible Impact Damage (BVID) detection
Artificial neural networks (ANN) was used by Benitez et al [15] to reduce the effects of uneven heating and flatness on inspection
Summary
Due to its excellent material properties such as low density, high strength, corrosion resistance, and high-freedom design characteristics, composite materials play an increasingly essential role in the field of automotive [1] and aviation industries [2]. J. Zhou is with the School of Aerospace, Transport and Manufacturing, Cranfield University, MK43 0AL, Bedfordshire, U.K, and Chengdu Aircraft. A CFRP impact damage inspection method was proposed by Zhang et al [10] based on manifold learning using ultrasonic induced thermography for BVID detection. In these studies, the geometry and the size of damaged areas are usually used to characterise and identify the degree of impact damage in CFRP [11]. Artificial neural networks (ANN) was used by Benitez et al [15] to reduce the effects of uneven heating and flatness on inspection They use the thermal contrast curve to detect and evaluate the depth of defects. A pattern recognition method is proposed to understand the uncertainty of the damage contours
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
