Digital Twin

A hybrid physics–data-driven reduced-order modeling framework is proposed for aerodynamic load inversion under structural field uncertainty.

A fleet-level digital twin method is developed for collaborative structural damage diagnosis and prognosis based on inter-aircraft similarity.

A parametric symbolic regression framework is proposed to discover unified crack growth models from multi-source experimental data.

A real-time load tracking method combining deep learning and an improved inverse–direct approach enables sensor-free airframe monitoring.

By seamlessly integrating a reduced-order digital twin containing damage states and influencing parameters as a decoder within the variational neural network，it enables the individualized, real-time structural damage quantification and parameter calibration across an entire fleet, while accounting for uncertainties.

This paper presents a comprehensive and integrated framework for constructing the digital twin of an Unmanned Aerial Vehicle, incorporating load tracking, multi-level structural analysis, and probabilistic diagnosis and prognosis.

This integrated approach facilitates real-time monitoring of full-field load distribution, relying solely on flight parameters.

This study introduces a reduced-order modeling (ROM) method for predicting nonplanar crack growth in structural digital twins.

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.

A deep learning-based flight data upsampling method is proposed to effctively enhances the resolution of flight data.