1–6 Jun 2025
Taipei International Convention Center (TICC)
Asia/Taipei timezone

Automated conditioning utilizing machine learning: first experimental results

MOPM079
2 Jun 2025, 16:00
2h
Exhibiton Hall A _Magpie (TWTC)

Exhibiton Hall A _Magpie

TWTC

Poster Presentation MC1.A08 Linear Accelerators Monday Poster Session

Speaker

Stephan Wagner (Goethe University Frankfurt)

Description

The conditioning of room temperature cavities is a long process. Additionally, since the cavity or auxiliary equipment can be damaged, constant supervision or extensive safety precautions are required. To reduce the workload for everyone involved and to increase the efficiency of the conditioning process, it was decided to develop a machine learning algorithm with the goal of fully automated conditioning in mind.
The initial model was trained on available data of the low energy-domain (up to 500 W). Since it was possible to expand the data to higher power levels during conditionings in 2024, the algorithm is now trained for power levels up to 30 kW. In this paper, the challenges of training with different power scales, as well as the first experimental results shall be discussed.

Region represented Europe
Paper preparation format LaTeX

Author

Stephan Wagner (Goethe University Frankfurt)

Co-authors

Holger Podlech (Goethe University Frankfurt) Klaus Kümpel (Goethe University Frankfurt)

Presentation materials

There are no materials yet.