An adaptive guided wave-Gaussian mixture model for damage monitoring under time-varying conditions: Validation in a full-scale aircraft fatigue test

Structural health monitoring technology has gradually developed from the research in laboratory to engineering validations and applications. However, the problem of reliable damage evaluation under time-varying conditions is a main obstacle for applying structural health monitoring to real aircraft structures. Among the existing structural health monitoring methods, the guided wave–based structural health monitoring method is popular but the time-varying problem needs to be addressed. Several methods have been proposed to deal with this problem but limitations remain. In this article, an adaptive guided wave-Gaussian mixture model–based damage monitoring method is proposed. It can be used online without any structural mechanical model and a priori knowledge of damage under time-varying conditions. With this method, a baseline guided wave-Gaussian mixture model is constructed first based on the guided wave features obtained under time-varying conditions when the structure is in healthy state. When a new guided wave feature is obtained during an online damage monitoring process, the guided wave-Gaussian mixture model is updated by an adaptive updating mechanism including dynamic learning and Gaussian components split-merge. The mixture probability structure of the guided wave-Gaussian mixture model and the number of Gaussian components can be optimized adaptively. Finally, a probability damage index is proposed to measure the degree of variation between the baseline guided wave-Gaussian mixture model and the online guided wave-Gaussian mixture model to reveal the damage-induced weak cumulative variation trend of the guided wave-Gaussian mixture model so as to increase the damage evaluation reliability. The method is validated in a full-scale aircraft fatigue test, and the results indicate that the reliable crack growth monitoring of the right landing gear spar and the left wing panel under the fatigue load condition is achieved.