Speaker
Description
Accelerator operators and beamline users can highly benefit from accurate and efficient measurements of FEL (free-electron laser) pulse power profiles. The use of machine learning to predict such profiles is an area of rapid development in the field. This work presents recent measurements and tests at the FLASH FEL at DESY of an image-based machine learning application developed to facilitate online FEL power profile reconstruction. The reconstruction has been performed using machine learning predictions of the longitudinal phase-space (LPS) of electron beams unaffected by the FEL process, originally measured using a transverse deflecting structure. The predictions were used in combination with longitudinal measurements of the LPS of the electron beam after lasing, which does not interfere with delivery to users, to reconstruct the FEL pulse. The results of the reconstruction process have been validated by comparison with a reference method which does not rely on machine learning.
| In which format do you inted to submit your paper? | LaTeX |
|---|---|
| Preprint marking on your proceeding paper | I do not wish my paper to be marked as preprint. |
| I no longer wish to present this contribution, please withdraw it. | Keep my contribution |