Manifold learning-based feature extraction for structural defect reconstruction

TL;DR

This paper introduces NetInv, a deep learning framework that improves the accuracy and efficiency of reconstructing structural defects from ultrasonic guided wave data, advancing non-destructive testing methods.

Contribution

The paper presents a novel deep learning-based approach, NetInv, for defect reconstruction that outperforms traditional methods in quality and speed.

Findings

NetInv achieves higher quality defect profiles.

NetInv demonstrates remarkable efficiency.

Provides insights for data-driven structural health monitoring.

Abstract

Data-driven quantitative defect reconstructions using ultrasonic guided waves has recently demonstrated great potential in the area of non-destructive testing. In this paper, we develop an efficient deep learning-based defect reconstruction framework, called NetInv, which recasts the inverse guided wave scattering problem as a data-driven supervised learning progress that realizes a mapping between reflection coefficients in wavenumber domain and defect profiles in the spatial domain. The superiorities of the proposed NetInv over conventional reconstruction methods for defect reconstruction have been demonstrated by several examples. Results show that NetInv has the ability to achieve the higher quality of defect profiles with remarkable efficiency and provides valuable insight into the development of effective data driven structural health monitoring and defect reconstruction using machine learning.