Symmetry constrained neural networks for detection and localization of damage in metal plates
This work addresses structural health monitoring for metal plates, but it is incremental as it applies existing neural network methods with symmetry constraints to a specific experimental setup.
The paper tackled damage detection and localization in a thin aluminum plate using deep learning on Lamb wave data, achieving over 99% detection accuracy and 2.58 ± 0.12 mm mean localization error.
The present paper is concerned with deep learning techniques applied to detection and localization of damage in a thin aluminum plate. We used data collected on a tabletop apparatus by mounting to the plate four piezoelectric transducers, each of which took turn to generate a Lamb wave that then traversed the region of interest before being received by the remaining three sensors. On training a neural network to analyze time-series data of the material response, which displayed damage-reflective features whenever the plate guided waves interacted with a contact load, we achieved a model that detected with greater than $99\%$ accuracy in addition to a model that localized with $2.58 \pm 0.12$ mm mean distance error. For each task, the best-performing model was designed according to the inductive bias that our transducers were both similar and arranged in a square pattern on a nearly uniform plate.