JACoW logo

Journals of Accelerator Conferences Website (JACoW)

JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.


RIS citation export for TUP38: Deep Neural Network for Beam Profile Classification in Synchrotron

TY  - CONF
AU  - Piekarski, M.
ED  - Forck, Peter
ED  - Wawrzyniak, Adriana
ED  - Schaa, Volker R.W.
ED  - Kowalski, Grzegorz W.
ED  - Cudek, Agnieszka (SOLARIS, Kraków
TI  - Deep Neural Network for Beam Profile Classification in Synchrotron
J2  - Proc. of IBIC2022, Kraków, Poland, 11-15 September 2022
CY  - Kraków, Poland
T2  - International Beam Instrumentation Conference
T3  - 11
LA  - english
AB  - The main goal of NSRC SO­LARIS is to pro­vide sci­en­tific com­mu­nity with high qual­ity syn­chro­tron light. To achieve this, it is necessary to constantly monitor many subsystems responsible for beam stability and to analyze data about the beam itself from various diagnostic beamlines. In this work a deep neural net­work for transverse beam profile classification is pro­posed. Main task of the system is to automatically assess and classify transverse beam profiles based solely on the evaluation of the beam image from the Pinhole diagnostic beamline at SOLARIS. At the present stage, a binary assignment of each profile is performed: stable beam operation or unstable beam operation / no beam. Base model architecture consists of a pre-trained con­vo­lu­tional neural net­work followed by a densely-connected classifier and the system reaches accuracy at the level of 90%. The model and the results obtained so far are discussed, along with plans for future development.
PB  - JACoW Publishing
CP  - Geneva, Switzerland
SP  - 323
EP  - 326
KW  - network
KW  - diagnostics
KW  - operation
KW  - emittance
KW  - synchrotron
DA  - 2022/12
PY  - 2022
SN  - 2673-5350
SN  - 978-3-95450-241-7
DO  - doi:10.18429/JACoW-IBIC2022-TUP38
UR  - https://jacow.org/ibic2022/papers/tup38.pdf
ER  -