Structural Crack Imaging Under Temperature Variation Based on Gaussian Mixture Model and Guided Wave

The environment and operation conditions (EOCs) of aircraft structures pose a significant challenge for advancing structural health monitoring from laboratory to practical applications. To address this problem, a Gaussian mixture model (GMM) and guided wave (GW) based imaging method is presented here for effective crack monitoring in aircraft metal structures under the influence of EOCs. In this method, in order to suppress the EOCs introduced uncertain influence and to generate EOCs independent feature signal, which is solely influenced by structural damages, the GMM is adopted. During the monitoring process, utilizing the derived EOCs independent feature signals enables the execution of GW imaging, yielding a damage map that facilitates accurate damage localization. The method is validated on a perforated aluminum plate from <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$-50{}^{\circ}\mathrm{C}$</tex> to <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$80^{\circ}\mathrm{C}$</tex>, confirming reliable damage imaging and localization.