Answers are grounded in this paper and cite their sources.
Digital twin technology establishes a mapping relationship between the physical and digital spaces through digital means, enabling bidirectional information exchange between the virtual and physical worlds. It also facilitates real-time prediction and updates of multi-source information that is difficult to directly acquire from the physical space, making it a crucial tool in structural health monitoring. However, current structural health monitoring still faces challenges in spatiotemporal collaborative dynamic prediction and multi-model integration under complex loading conditions, resulting in deficiencies in real-time performance and accuracy. This study proposes a Spatiotemporal Collaborative Digital Twin (SC-DT) structural health monitoring method based on dynamic multi-fidelity models. The method integrates numerical simulation, dynamic multi-fidelity modeling, surrogate prediction, machine learning, and fatigue life prediction techniques to achieve spatiotemporal collaborative monitoring of structural health. It enables real-time stress prediction while concurrently identifying stress cycles under varying loading conditions and quantifying cumulative damage effects. By dynamically adjusting the model fidelity, it effectively balances computational cost and accuracy. Using an aircraft wing as a case study, this paper provides a detailed explanation of the SC-DT method's principles and implementation. The validity of the method is verified by comparing experimental measurements with SC-DT predictions. Compared to traditional finite element methods, SC-DT significantly reduces the computational time cost of structural performance analysis. In the case of the aircraft wing, the method achieves real-time predictions in 0.2 s, offering a novel solution for real-time health monitoring of complex structures.
No takes yet. Share an insight, caveat, or question.
Lu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: