Manifold learning-based feature extraction for structural defect reconstruction
This addresses defect reconstruction in non-destructive testing for structural health monitoring, representing an incremental improvement over existing methods.
The paper tackles the problem of structural defect reconstruction from ultrasonic guided waves by developing NetInv, a deep learning framework that maps reflection coefficients to defect profiles. Results show NetInv achieves higher quality defect profiles with remarkable efficiency compared to conventional methods.
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.