Symmetry constrained neural networks for detection and localization of damage in metal plates

TL;DR

This paper presents a symmetry-constrained neural network approach for accurately detecting and localizing damage in metal plates using Lamb wave data, leveraging transducer arrangement and deep learning.

Contribution

It introduces a neural network model that incorporates symmetry constraints based on transducer placement for improved damage detection and localization in metal plates.

Findings

Detection accuracy exceeds 99%

Localization mean error is 2.58 mm

Symmetry constraints improve model performance

Abstract

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.