Christoph Humer, Simon Höll, Christoph Kralovec-Rödhammer, Martin Schagerl,
"Physics-driven Deep Neural Networks for Damage Identification using Guided Wave Damage Interaction Coefficients"
, in Christian Boller: Proceedings of the 11th European Workshop on Structural Health Monitoring (EWSHM 2024), e-Journal of Nondestructive Testing, 7-2024
Original Titel:
Physics-driven Deep Neural Networks for Damage Identification using Guided Wave Damage Interaction Coefficients
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the 11th European Workshop on Structural Health Monitoring (EWSHM 2024)
Original Kurzfassung:
In this paper, recent advancements in the development of a guided wave-based damage identification approach using wave damage interaction coefficients (WDICs) and deep neural networks (DNNs) are presented. These WDICs uniquely describe the complex scattering of guided waves around possible damages and depend on the properties of the damage itself. Hence, they are utilized as physics-based and highly sensitive damage features herein. It is demonstrated, that DNNs can effectively learn intricate relationships between damage characteristics and complex-shaped WDIC patterns from a compact sized training dataset. In this study, two training datasets are created by numerical finite element simulations and experimental scanning laser Doppler vibrometer measurements using a pseudo-damage approach. Therefore, the orientation and thickness of surface-bonded artificial damages are varied to generate the training data of 12 selected damage scenarios.
The generalization capabilities of the fully trained DNNs allow to accurately predict WDICs even for damage scenarios unseen during training. The presented damage identification method leverages this powerful ability to characterize properties of unknown damages. Once trained, the precise DNN predictions become available promptly and can be compared with measured WDICs from an unknown damage for selected sensor positions. The identification results of the experiment-based approach are highly accurate for the tested damage scenario. For the simulation-based approach the structural differences between the numerical and experimental scattering patterns cause misidentifications. Therefore, the influence of the adhesive layer in the numerical model is discussed. Furthermore, the potential of using the real and imaginary parts of the complex-valued WDICs in the damage identification are highlighted.
Forschungs-