| Title |
Neural Network Based Generalized Predictive Control for RFT-30 Cyclotron System |
| Authors |
- Y.B. Kong, M.G. Hur, E.J. Lee, J.H. Park, S.D. Yang
KAERI, Jeongeup-si, Republic of Korea
- Y.D. Park
Advanced Radiation Technology Institute, Korea Atomic Energy Research Institute, Jeongup-si, Jeollabuk-do, Republic of Korea
|
| Abstract |
Beamline tuning is time consuming and difficult work in accelerator system. In this work, we propose a neural generalized predictive control (NGPC) approach for the RFT-30 cyclotron beamline. The proposed approach performs system identification with the NN model and finds the control parameters for the beamline. Performance results show that the proposed approach helps to predict optimal parameters without real experiments with the accelerator.
|
| Paper |
download TUP19.PDF [0.780 MB / 3 pages] |
| Conference |
Cyclotrons2016, Zurich, Switzerland |
| Series |
International Conference on Cyclotrons and Their Applications (21st) |
| Proceedings |
Link to full Cyclotrons2016 Proccedings |
| Session |
Poster Session: Cyclotron Technology |
| Date |
13-Sep-16 14:40–16:30 |
| Main Classification |
Cyclotron Technology |
| Keywords |
controls, cyclotron, network, simulation, target |
| Publisher |
JACoW, Geneva, Switzerland |
| Editors |
Jan Chrin (PSI, Villigen, Switzerland); Jacobus M. Schippers (PSI, Villigen, Switzerland); Mike Seidel (PSI, Villigen, Switzerland); Volker RW Schaa (GSI, Darmstadt, Germany) |
| ISBN |
978-3-95450-167-0 |
| Published |
January 2017 |
| Copyright |
|
