User: Guest  Login
Title:

Transfer Learning Enhanced Full Waveform Inversion*

Document type:
Konferenzbeitrag
Author(s):
Kollmannsberger, Stefan; Singh, Divya; Herrmann, Leon
Abstract:
We propose a way to favorably employ neural networks in the field of non-destructive testing using Full Waveform Inversion (FWI). The presented methodology discretizes the unknown material distribution in the domain with a neural network within an adjoint optimization. To further increase efficiency of the FWI, pretrained neural networks are used to provide a good starting point for the inversion. This reduces the number of iterations in the Full Waveform Inversion for specific, yet generalizabl...     »
Book / Congress title:
2023 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)
Publisher:
IEEE
Publisher address:
Seattle, WA, USA
Year:
2023
Month:
June
Pages:
866--871
Print-ISBN:
978-1-66547-633-1
Fulltext / DOI:
doi:10.1109/AIM46323.2023.10196158
 BibTeX