JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.
@inproceedings{velotti:ipac2022-tupost044,
author = {F.M. Velotti and M.J. Barnes and B. Goddard and I. Revuelta},
title = {{Fortune Telling or Physics Prediction? Deep Learning for On-Line Kicker Temperature Forecasting}},
booktitle = {Proc. IPAC'22},
% booktitle = {Proc. 13th International Particle Accelerator Conference (IPAC'22)},
pages = {957--960},
eid = {TUPOST044},
language = {english},
keywords = {kicker, operation, simulation, injection, network},
venue = {Bangkok, Thailand},
series = {International Particle Accelerator Conference},
number = {13},
publisher = {JACoW Publishing, Geneva, Switzerland},
month = {07},
year = {2022},
issn = {2673-5490},
isbn = {978-3-95450-227-1},
doi = {10.18429/JACoW-IPAC2022-TUPOST044},
url = {https://jacow.org/ipac2022/papers/tupost044.pdf},
abstract = {{The injection kicker system MKP of the Super Proton Synchrotron SPS at CERN is composed of 4 kicker tanks. The MKP-L tank provides additional kick needed to inject 26 GeV Large Hadron Collider LHC 25 ns type beams. This device has been a limiting factor for operation with high intensity, due to the magnet’s broadband beam coupling impedance and consequent beam induced heating. To optimise the usage of the SPS and avoid idle (kicker cooling) time, studies were conducted to develop a recurrent deep learning model that could predict the measured temperature evolution of the MKP-L, using the beam conditions and temperature history as input. In a second stage, the ferrite temperature is also estimated putting together the external temperature predictions from accurate thermo-mechanical simulations of the kicker magnet. In this paper, the methodology is described and details of the neural network architecture used, together with the implementation of an ad-hoc loss function, are given. The results applied to the SPS 2021 operational data are presented.}},
}