Neural networks trained on 3D energy deposition maps recover signal fraction and photon multiplicity from simulated ultrafast pileup, outperforming depth-ratio baselines.
The Next Generation of MeV Energy X-ray Sources for use in the Inspection of Additively Manufactured Parts for Industry
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
For the first time, we demonstrate the application of an inverse Compton scattering X-ray Source, driven by a laser-plasma accelerator, to image an additively manufactured component. X-rays with a mean energy of 380 keV were produced and used to image an additively manufactured part made of an Inconel (Nickel 718) alloy. Because inverse Compton scattering driven by laser-plasma acceleration produces high-energy X-rays while maintaining a focal spot size on the order of a micron, the source can provide several benefits over conventional X-ray production methods, particularly when imaging superalloy parts, with the potential to revolutionise what can be inspected.
citation-role summary
background 1
citation-polarity summary
fields
physics.ins-det 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Machine learning methods for spectroscopic information recovery under ultrafast photon pileup
Neural networks trained on 3D energy deposition maps recover signal fraction and photon multiplicity from simulated ultrafast pileup, outperforming depth-ratio baselines.