Benutzer: Gast  Login
Titel:

Transfer Learning Enhanced Full Waveform Inversion*

Dokumenttyp:
Konferenzbeitrag
Autor(en):
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...     »
Kongress- / Buchtitel:
2023 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)
Verlag / Institution:
IEEE
Verlagsort:
Seattle, WA, USA
Jahr:
2023
Monat:
June
Seiten:
866--871
Print-ISBN:
978-1-66547-633-1
Volltext / DOI:
doi:10.1109/AIM46323.2023.10196158
 BibTeX