The proposed approach improves prediction accuracy compared to traditional individual-based methods and effectively controls uncertainties for each structure, even during intervals of no observations.

The proposed strategy utilizes two connected probabilistic processes, which conduct the diagnosis/prognosis and calculate the inspection intervals, respectively, to adaptively set the inspection intervals according to the updating of the digital twin model.

A state-of-the-art online damage quantification framework based on domain adaptation is presented, and comprehensively demonstrated with a damaged helicopter panel.

A novel domain adaptation method is proposed to assist diagnostic tasks based on labeled data from similar structures or simulations and is then applied to cracked lap shear specimens to assist debonding quantification.

In this paper, a reduced-order simulation approach is developed by leveraging the symmetric Galerkin boundary element method–finite element method (SGBEM-FEM) coupling method and machine learning methods to realize a real-time prediction of probabilistic crack growth in complex structures with minimum computational burden.