Keyword: network
Paper Title Other Keywords Page
MOPP024 Development of New Loss Monitor Electronics for the HIPA Facility hardware, electron, Linux, ISOL 140
 
  • R. Dölling, E. Johansen, W. Koprek, D. Llorente Sancho, M. Roggli
    PSI, Villigen PSI, Switzerland
 
  A replacement for the ageing electronics of loss monitors at HIPA is under development. We discuss requirements, concepts and first tests of a prototype.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IBIC2019-MOPP024  
About • paper received ※ 04 September 2019       paper accepted ※ 08 September 2019       issue date ※ 10 November 2019  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEBO04 Enhancement of the S-DALINAC Control System with Machine Learning Methods target, controls, linac, electron 473
 
  • J.H. Hanten, M. Arnold, J. Birkhan, C. Caliari, N. Pietralla, M. Steinhorst
    TU Darmstadt, Darmstadt, Germany
 
  Funding: *Work supported by DFG through GRK 2128
For the EPICS-based control system of the superconducting Darmstadt electron linear accelerator S-DALINAC**, supporting infrastructures based on machine learning are currently developed. The most important support for the operators is to assist the beam setup and controlling with reinforcement learning using artificial neural networks. A particle accelerator has a very large parameter space with often hidden relationships between them. Therefore neural networks are a suited instrument to use for approximating the needed value function which represents the value of a certain action in a certain state. Different neural network structures and their training with reinforcement learning are currently tested with simulations. Also there are different candidates for the reinforcement learning algorithms such as Deep-Q-Networks (DQN) or Deep-Deterministic-Policy-Gradient (DDPG). In this contribution the concept and first results will be presented.
**N. Pietralla, Nuclear Physics News, Vol. 28, No.2, 4 (2018)
 
slides icon Slides WEBO04 [2.073 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IBIC2019-WEBO04  
About • paper received ※ 03 September 2019       paper accepted ※ 09 September 2019       issue date ※ 10 November 2019  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPP007 Calibration for Beam Energy Position Monitor System for Riken Superconducting Acceleration Cavity linac, cyclotron, impedance, synchrotron 519
 
  • T. Watanabe, M. Fujimaki, N. Fukunishi, H. Imao, O. Kamigaito, N. Sakamoto, Y. Watanabe, K. Yamada
    RIKEN Nishina Center, Wako, Japan
  • K. Hanamura, T. Kawachi
    Mitsubishi Electric System & Service Co., Ltd, Tsukuba, Japan
  • A. Kamoshida
    National Instruments Japan Corporation, MInato-ku, Tokyo, Japan
  • R. Koyama
    SHI Accelerator Service Ltd., Tokyo, Japan
  • A. Miura
    JAEA/J-PARC, Tokai-mura, Japan
  • T. Miyao, T. Toyama
    KEK, Ibaraki, Japan
 
  Upgrades for the RIKEN Heavy-ion Linac (RILAC) involving a new Superconducting Linac (SRILAC) are currently underway to promote super-heavy element searches and Radio Isotope (RI) production (211At) for medical use at the RIKEN radioactive isotope beam factory (RIBF). If destructive monitors are used, since they generate outgassing, it becomes difficult to maintain the Q value and surface resistance indicating the performance of the superconducting radio frequency (SRF) cavities over a long period of time. Therefore it is crucially important to develop nondestructive beam measurement diagnostics. We have developed a beam energy position monitor (BEPM) system which can measure not only the beam position but also the beam energy simultaneously by measuring the time of flight of the beam. By using parabolic cut, ideal linear response of the quadrupole moments is realized, keeping a good linear position sensitivity at the same time. We fabricated 11 BEPMs and the position calibration system employing a wire method has been used to obtain the sensitivity and offset of BEPMs. We will describe details concerning the BEPM, calibration system and measured results.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IBIC2019-WEPP007  
About • paper received ※ 05 September 2019       paper accepted ※ 10 September 2019       issue date ※ 10 November 2019  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPP021 Machine Learning Image Processing Technology Application in Bunch Longitudinal Phase Data Information Extraction damping, injection, synchrotron, SRF 561
 
  • X.Y. Xu, Y.M. Zhou
    SINAP, Shanghai, People’s Republic of China
  • Y.B. Leng, Y.M. Zhou
    SSRF, Shanghai, People’s Republic of China
  • X.Y. Xu
    University of Chinese Academy of Sciences, Beijing, People’s Republic of China
 
  To achieve the bunch-by-bunch longitudinal phase measurement, Shanghai Synchrotron Radiation Facility (SSRF) has developed a high resolution measurement system. We used this measurement system to study the injection transient process, and obtained the longitudinal phase of the refilled bunch and the longitudinal phase of the original stored bunch. A large number of parameters of the synchronous damping oscillation are included in this large amount of longitudinal phase data, which are important for the evaluation of machine state and bunch stability. The multi-turn phase data of a multi-bunch is a large two-dimensional array that can be converted into an image. The convolutional neural network (CNN) is a machine learning model with strong capabilities in image processing. We hope to use the convolutional neural network to process the longitudinal phase two-dimensional array data, and extract important parameters such as the oscillation amplitude and the synchrotron damping time.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IBIC2019-WEPP021  
About • paper received ※ 23 August 2019       paper accepted ※ 10 September 2019       issue date ※ 10 November 2019  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)