JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.
TY - CONF AU - Kim, D.-H. AU - Dang, J.J. AU - Kim, H.S. AU - Kwon, H.-J. AU - Lee, S. AU - Yun, S.P. ED - McIntosh, Peter ED - Burt, Graeme ED - Apsimon, Robert ED - Schaa, Volker R.W. TI - Machine Learning for Beam Orbit Correction at KOMAC Accelerator J2 - Proc. of LINAC2022, Liverpool, UK, 28 August-02 September 2022 CY - Liverpool, UK T2 - International Linear Accelerator Conference T3 - 31 LA - english AB - There are approaches to apply machine learning (ML) techniques to efficiently operate and optimize particle accelerators. Deep neural networks-based model is applied to experiments, correcting beam orbit through the low energy beam transport at the proton injector test stand. For more complex applications, time-series analysis model is studied to predict beam orbit in the 100-MeV beamline at KOMAC. This paper describes experimental data to train neural networks model, and presents the performance of the machine learning models. PB - JACoW Publishing CP - Geneva, Switzerland SP - 848 EP - 850 KW - network KW - proton KW - controls KW - linac KW - diagnostics DA - 2022/09 PY - 2022 SN - 2226-0366 SN - 978-3-95450-215-8 DO - doi:10.18429/JACoW-LINAC2022-THPORI02 UR - https://jacow.org/linac2022/papers/thpori02.pdf ER -