Keyword: network
Paper Title Other Keywords Page
MOPML068 Training the Next Generation of Accelerator Experts FEL, laser, electron, synchrotron 564
 
  • C.P. Welsch
    The University of Liverpool, Liverpool, United Kingdom
  • C.P. Welsch
    Cockcroft Institute, Warrington, Cheshire, United Kingdom
 
  Funding: Work supported by the European Union under grant agreements no 215080, 289191, 289485, 675265 and 721559.
Close collaboration between academia, research centres and industry has turned out to be crucial for the advancement of accelerator science and technology. It is also ideal for providing an efficient training of the next generation of particle accelerator experts and for linking the global accelerator community. Five international research and training networks (DITANET, oPAC, LA3NET, OMA and AVA) have been initiated and coordinated by the University of Liverpool/Cockcroft Institute since 2007. These networks have provided training to almost 100 Fellows from all over the world and organised dozens of international schools, topical workshops and international conferences for the accelerator community. The research activities of the networks have led to hundreds of journal publications and conference proceedings. This contribution presents the best practice in establishing such international collaborative projects, how to establish successful links between sectors and countries, and highlights the main research results that resulted from the research programs.
 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-MOPML068  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPAF022 Application of Machine Learning to Minimize Long Term Drifts in the NSLS-II Linac klystron, linac, operation, booster 1867
 
  • R.P. Fliller, C. Gardner, P. Marino, R.S. Rainer, M. Santana, G.J. Weiner, X. Yang, E. Zeitler
    BNL, Upton, Long Island, New York, USA
 
  Funding: This manuscript has been authored by Brookhaven Science Associates, LLC under Contract No. DE-SC0012704 with the U.S. Department of Energy
Machine Learning has proven itself as a useful technique in a variety of applications from image recognition to playing Go. Artificial Neural Networks have certain advantages when used as a feedforward system, such as the predicted correction relies on a model built from data. This allows for the Artificial Neural Network to compensate for effects that are difficult to model such as low level RF adjustments to compensate for long term drifts. The NSLS-II linac suffers from long terms drifts from a number of sources including thermal drifts and klystron gain variations. These drifts have an effect on the injection efficiency into the booster, and if left unchecked, portions of the bunch train may not be injected into the booster, and the storage ring bunch pattern will ultimately suffer. In this paper, we discuss the application of Artificial Neural Networks to compensate for long term drifts in the NSLS-II linear accelerator. The Artificial Neural Network is implemented in python allowing for rapid development of the network. We discuss the design and training of the network, along with results of using the network in operation.
 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPAF022  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPAF058 Detection of X-Rays and Charged Particles via Detuning of the Microwave Resonator coupling, resonance, monitoring, experiment 1958
 
  • S.P. Antipov
    Euclid TechLabs, LLC, Solon, Ohio, USA
  • S.V. Kuzikov
    Euclid Beamlabs LLC, Bolingbrook, USA
  • S. Stoupin
    Cornell University (CLASSE), Cornell Laboratory for Accelerator-Based Sciences and Education, Ithaca, New York, USA
  • A.A. Vikharev
    IAP/RAS, Nizhny Novgorod, Russia
 
  Funding: DOE SBIR
Critically coupled microwave resonator is a finely balanced system, reflection at the resonance is virtually zero. Small changes in dielectric properties of resonator parts destroy this balance, small reflection can be detected from the resonator. This measurement is used in electron paramagnetic resonance studies. In this paper we discuss two accelerator - related applications of this technology. First is related to beam halo measurement taking advantage of high sensitivity of the microwave measurement. High energy particles crossing the diamond inside of a tuned resonator induce a weak conductivity in the sensing material. This small change results in resonator decoupling providing a signal proportional to a number of particles crossing the diamond plate. Second application considered is the x-ray flux monitoring. In this case it is x-ray induced photoconductivity which alters resonator coupling and produces a signal. Interestingly, sensing dielectric material embedded in a resonator can be a diamond or kapton window, refractive lens or part of a silicon monochromator. Thus an inevitable x-ray absorption on optical elements of the beamline is used to monitor x-ray flux online.
 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPAF058  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPAF062 Machine Learning Methods for Optics Measurements and Corrections at LHC optics, controls, quadrupole, data-analysis 1967
 
  • E. Fol, F.S. Carlier, J.M. Coello de Portugal, A. Garcia-Tabares, R. Tomás
    CERN, Geneva, Switzerland
 
  The application of machine learning methods and concepts of artificial intelligence can be found in various industry and scientific branches. In Accelerator Physics the machine learning approach has not found a wide application yet. This paper is devoted to evaluation of machine learning methods aiming to improve the optics measurements and corrections at LHC. The main subjects of the study are devoted to recognition and analysis of faulty beam position monitors and prediction of quadrupole errors using clustering algorithms, decision trees and artificial neural networks. The results presented in this paper clearly show the suitability of machine learning methods for the optics control at LHC and the potential for further investigation on appropriate approaches.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPAF062  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPAK008 Reconstructing Space-Charge Distorted IPM Profiles with Machine Learning Algorithms electron, simulation, space-charge, GUI 2099
 
  • D.M. Vilsmeier, M. Sapinski, R. Singh
    GSI, Darmstadt, Germany
  • J.W. Storey
    CERN, Geneva, Switzerland
 
  Measurements of undistorted transverse profiles via Ionization Profile Monitors (IPMs) may pose a great challenge for high brightness or high energy beams due to interaction of ionized electrons or ions with the electromagnetic field of the beam. This contribution presents application of various machine learning algorithms to the problem of reconstructing the actual beam profile from measured profiles that are distorted by beam space-charge interaction. (Generalized) linear regression, artificial neural network and support vector machine algorithms are trained with simulation data, obtained from the Virtual-IPM simulation tool, in order to learn the relation between distorted profiles and original beam dimension. The performance of different algorithms is assessed and the obtained results are very promising for testing with simulation data.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPAK008  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPAL030 Deep Learning Based Predictive Control for RFT-30 Cyclotron controls, cyclotron, simulation, operation 2230
 
  • Y.B. Kong, M.G. Hur, E.J. Lee, J.H. Park, H.S. Song, S.D. Yang
    KAERI, Jeongeup-si, Republic of Korea
 
  Successful construction of the control system is an important problem in the accelerator. The RFT-30 cyclotron is 30 MeV cyclotron for radioisotope production and fundamental researches. To operate the RFT-30 cyclotron for beam irradiation, the human operators should carefully manipulate the control parameters. If the control does not function properly, it becomes difficult to handle the cyclotron and cannot perform the accurate operations for the control. In this work, we propose a deep learning based model predictive control approach for the RFT-30 cyclotron. The proposed approach is composed of two steps: system identification and a control design. In the system identification procedure, the proposed approach constructs the predictive model of the accelerator using the deep learning approach. In the control design stage, the controller finds the optimal control inputs by solving the optimization problem. To analyze the performance of the proposed approach, we applied the approach into the RFT-30 cyclotron.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPAL030  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPAL048 Control Command Strategy for the ThomX Accelerator controls, HOM, TANGO, GUI 2284
 
  • H. Guler, N. ElKamchi, P. Gauron, H. Monard
    LAL, Orsay, France
 
  ThomX is an accelerator project designed to create a compact X Compton Backscattering Source for medical and cultural heritage applications. Control-Command (CC) system is a central part for the commissionning. ThomX CC is designed with TANGO SCADA system. This framework allows to control several devices from several places with the same SCADA System. TANGO Device Servers are software programs allowing to control devices and to implement data processing and presentation layers. For commissionning, experts need to access values of each device in a convenient way to allow them to modify parameters and check effect of a configuration on hardware. CC is a key part for this stage. Several GUI have been designed and gathered into several panels in collaboration with each expert group to gather their needs.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPAL048  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPMF035 Investigating the Effect of Inhomogeneous Resistivity on Bulk RRR and Heat Conductivity Using a Lattice Green's Functions Method cavity, niobium, lattice, HOM 2436
 
  • N.C. Shipman, A. Macpherson
    CERN, Geneva, Switzerland
  • G. Burt
    Cockcroft Institute, Lancaster University, Lancaster, United Kingdom
  • J.A. Mitchell
    Lancaster University, Lancaster, United Kingdom
 
  A method was developed to calculate the bulk RRR (residual resistivity ratio) which would be measured on a superconducting cavity or sample with an inhomogeneous resistivity and arbitrary geometry. The method involves modelling the object as a network of resistors and employs lattice Green's functions. A further adaptation of the method which allows the heat transport characteristics of such an object to be predicted is also described.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPMF035  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPMF065 High Efficiency, High Power, Resonant Cavity Amplifier For PIP-II cavity, coupling, impedance, operation 2518
 
  • M.P.J. Gaudreau, N. Butler, D.B. Cope, P. H. Gordon, E.G. Johnson, M.K. Kempkes, R.E. Simpson
    Diversified Technologies, Inc., Bedford, Massachusetts, USA
 
  Funding: Funded under US DOE grant no. DE-SC0015780
Diversified Technologies, Inc. (DTI) is developing an integrated resonant-cavity combined solid-state amplifier for the Proton Improvement Plan-II (PIP-II) at Fermilab. The prototype has demonstrated multiple-transistor combining at 71% efficiency, at 675 watts per transistor at 650 MHz. The design simplifies solid-state transmitters to create straightforward scaling to high power levels. A crucial innovation is the reliable "soft-failure" mode of operation; a failure in one or more of these myriad combined transistors has negligible performance impact. The design couples the transistor drains directly to the cavity without first transforming to 50 Ohms, avoiding the otherwise-necessary multitude of circulators, cables, and connectors. DTI's design increases the power level at which it is cost-effective to employ a solid-state transmitter. DTI is upgrading the system to accommodate more transistors in each cavity module, and then will design and build a complete 100 kW-class transmitter which will consist of four such cavity modules and a combiner.
 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPMF065  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPMF080 Investigation and Estimation of the LHC Magnet Vibrations Induced by HL-LHC Civil Engineering Activities civil-engineering, operation, experiment, monitoring 2568
 
  • M. Guinchard, M. Cabon, C. Charrondière, K. Develle, P. Fessia, L.L. Lacny, J.A. Osborne, L.S. Scislo, J. Wenninger
    CERN, Geneva, Switzerland
 
  HL-LHC requires the excavation of large underground infrastructures in order to host new equipment. The tunnel shall be ready for installation for LS3 (2022) and therefore its construction shall take in place in parallel with the LHC exploitation. Effect of vibrations induced by civil engineering activities need to be evaluated in order to take required corrective actions. For this purpose, several diverse measurements and experiments have been performed in order to estimate the vibration sources and determine the vibration transfer path through the floor and the structure. The transfer functions from amplitude and phase point of view were determined through molasses rock, for both horizontal and vertical vibrations, with dedicated tools and Experimental Modal Analysis was carried out on mechanical structure. The campaign of measurements have been used to confirm the effect of the surface induced vibration on the circulating beam orbit at the resonance frequencies of the structure. This paper reviews the advanced technique of measurements, results and the conclusion about the impact of operating civil engineering machines (road header, hydraulic hammer) during beam exploitation.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPMF080  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPML016 Development of Nb3Sn Coatings for Superconducting RF Cavities at Fermilab cavity, SRF, factory, superconductivity 2718
 
  • S. Posen, S.K. Chandrasekaran, O.S. Melnychuk, D.A. Sergatskov, B. Tennis, Y. Trenikhina
    Fermilab, Batavia, Illinois, USA
  • J. Lee
    NU, Evanston, Illinois, USA
 
  Nb3Sn films are a promising alternative material for su-perconducting RF cavities, with proven high quality factors at medium fields and predictions for increased superheating field as well. In this contribution, we de-scribe the latest results from the Fermilab Nb3Sn SRF program. Early experiments have been focused on single cell 1.3 GHz cavities. We briefly review efforts to bring the parameters used in the coating process into a range where they produce uniform surfaces without regions showing signs of excess tin or thin/uncoated areas. We then present the latest cavity results, after modifications to the coating recipe based on feedback from film appear-ance and RF performance. These results show high Q0 at medium fields and a maximum field of ~18 MV/m.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPML016  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPML070 The Status of the CSNS/RCS Power Supply System power-supply, dipole, neutron, resonance 2850
 
  • X. Qi, Z. Hao, W. Zhang
    IHEP, Beijing, People's Republic of China
 
  The 1.6GeV proton synchrotron proposed in the CSNS Project is a 25Hz rapid-cycling synchrotron (RCS) with injection energy of 80MeV. Beam power is aimed to 100kW at 1.6GeV. In this year, the neutron beam was successfully obtained for the first time. This paper will introduce the commission statues of RCS Power Supply System status in the last year.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-WEPML070  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THYGBE1 Applying Artificial Intelligence to Accelerators FEL, controls, feedback, electron 2925
 
  • A. Scheinker, R.W. Garnett, D. Rees
    LANL, Los Alamos, New Mexico, USA
  • D.K. Bohler
    SLAC, Menlo Park, California, USA
  • A.L. Edelen, S.V. Milton
    CSU, Fort Collins, Colorado, USA
 
  Particle accelerators are being designed and operated over a wide range of complex beam phase space distributions. For example, the Linac Coherent Light Source (LCLS) upgrade, LCLS-II, is considering complex schemes such as two-color operation [1], while the plasma wake field acceleration facility for advanced accelerator experimental tests (FACET) upgrade, FACET-II, is planning on providing custom tailored current profiles [2]. Because of uncertainty due to limited diagnostics and time varying performance, such as thermal drifts, as well as collective effects and the complex coupling of large numbers of components, it is impossible to use simple look up tables for parameter settings in order to quickly switch between widely varying operating ranges. Several forms of artificial intelligence are currently being investigated in order to enable accelerators to quickly and automatically re-adjust component settings without human intervention. In this work we discuss recent progress in applying neural networks and adaptive feedback algorithms to enable automatic accelerator tuning and optimization.
[1] A. A. Lutman et al., Nat. Photonics 10.11, 745 (2016).
[2] V. Yakimenko et al., IPAC2016, Busan, Korea, 2016.
 
slides icon Slides THYGBE1 [14.261 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THYGBE1  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPAK088 Matrix Representation of Lie Transform in TensorFlow simulation, storage-ring, GPU, linear-dynamics 3438
 
  • A.N. Ivanov, S.N. Andrianov, N.V. Kulabukhova, A.A. Sholokhova
    St. Petersburg State University, St. Petersburg, Russia
  • E. Krushinevskii, E. Sboeva
    Saint Petersburg State University, Saint Petersburg, Russia
 
  In the article, we propose an implementation of the matrix representation of Lie transform using TensorFlow as a computational engine. TensorFlow allows easy description of deep neural networks and provides automatic code execution on both single CPU/GPU and cluster architectures. In this research, we demonstrate the connection of the matrix Lie transform with polynomial neural networks. The architecture of the neural network is described and realized in code. In terms of beam dynamics, the proposed technique provides a tool for both simulation and analysis of experimental results using modern machine learning techniques. As a simulation technique one operates with a nonlinear map up to the necessary order of nonlinearity. On the other hand, one can utilize TensorFlow engine to run map optimization and system identification problems.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPAK088  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPAL005 Construction and Commissioning of the S-Band High-Gradient RF Laboratory at IFIC klystron, GUI, linac, cathode 3619
 
  • D. Esperante Pereira, C. Blanch Gutiérrez, M. Boronat, J. Fuster, D. Gonzalez Iglesias, A. Vnuchenko
    IFIC, Valencia, Spain
  • N. Catalán Lasheras, G. McMonagle, I. Syratchev, W. Wuensch
    CERN, Geneva, Switzerland
  • A. Faus-Golfe
    LAL, Orsay, France
  • B. Gimeno
    UVEG, Burjasot (Valencia), Spain
 
  An S-Band High-Gradient (HG) Radio Frequency (RF) laboratory is under construction and commissioning at IFIC. The purpose of the laboratory is to perform investigations of high-gradient phenomena and to develop normal-conducting RF technology, with special focus on RF systems for hadron-therapy. The layout of the facility is derived from the scheme of the Xbox-3 test facility at CERN* and uses medium peak-power (7.5 MW) and high repetition rate (400 Hz) klystrons, whose RF output is combined to drive two testing slots to the required power. The design and construction of the various components of the system started in 2016 and has been completed. The installation and commissioning of the laboratory is progressing, with first results expected before mid 2018. The technical characteristics of the different elements of the system and the commissioning status together with preliminary results are described.
* N. Catalan Lasheras, et al., 'Commissioning of Xbox3: a very high capacity X-band RF test stand', Proc. LINAC2016, East Lansing, USA, September 2016.
 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPAL005  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPAL009 A TM01 Mode Launcher With Quadrupole Field Components Cancellation for High Brightness Applications GUI, quadrupole, gun, brightness 3631
 
  • G. Castorina
    INFN-Roma1, Rome, Italy
  • A.D. Cahill, J.B. Rosenzweig
    UCLA, Los Angeles, California, USA
  • F. Cardelli, G. Franzini, A. Marcelli, B. Spataro
    INFN/LNF, Frascati (Roma), Italy
  • L. Celona, S. Gammino, G. Torrisi
    INFN/LNS, Catania, Italy
  • V.A. Dolgashev
    SLAC, Menlo Park, California, USA
  • L. Ficcadenti
    Rome University La Sapienza, Roma, Italy
  • M. Migliorati, A. Mostacci, L. Palumbo
    Sapienza University of Rome, Rome, Italy
  • G. Sorbello
    University of Catania, Catania, Italy
 
  The R&D of high gradient radiofrequency (RF) devices is aimed to develop innovative accelerating structures based on new manufacturing techniques and materials in order to construct devices operating with the highest accelerating gradient. Recent studies have shown a large increase in the maximum sustained RF surface electric fields in copper structures operating at cryogenic temperatures. These novel approaches allow significant performance improvements of RF photoinjectors. Indeed the operation at high surface fields results in considerable increase of electron beam brilliance. This increased brilliance requires high field quality in the RF photoinjector and specifically in its power coupler. In this work we present a novel power coupler for the RF photoinjector. The coupler is a compact X-band TM01 mode launcher with a fourfold symmetry which minimized both the dipole and the quadrupole RF components.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPAL009  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPAL112 RF Matching Circuit for CANREB RFQ rfq, TRIUMF, simulation, pick-up 3902
 
  • T. Au, B. Barquest, J.J. Keir, V. Zvyagintsev
    TRIUMF, Vancouver, Canada
 
  A RF matching circuit has been developed to provide two phase RF voltage of 1.2 kVpp at 3 MHz and 6 MHz for the CANREB RFQ structure with an equivalent capacitive load of 300 pF. The RF matching circuit utilizes pi-network with two phase transformer. Beyond RF drive the CANREB structure requires pulse DC bias with amplitude up to 500 V. Results of development and testing of RF matching circuit and filters are presented in this paper.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPAL112  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPAL156 High-Power Test of a Compact X-Band RF Rotary Joint GUI, linac, cathode, electromagnetic-fields 4017
 
  • J. Liu, H.B. Chen, J.Q. Qiu, J. Shi, Z.H. Wang, X.W. Wu, H. Zha
    TUB, Beijing, People's Republic of China
 
  A compact X-band (9.3 GHz) RF rotary joint has been developed in the accelerator laboratory of Tsinghua University. Cold measurements on the rotary joint using Vector-Network showed good results. In recent high-power tests, the RF rotary joint was operated under a 1.6 MW X-band magnetron. The incident power, the transmitted power and the pulse width of this rotary joint have been measured. The transmitted power kept stable in different rotation angle. In this paper, the setup and results of the high-power tests of this RF rotary joint are presented.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPAL156  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPMK104 High Power and High Repetition Rate X-band Power Source Using Multiple Klystrons klystron, controls, GUI, MMI 4552
 
  • M. Volpi, M.J. Boland, P.J. Giansiracusa, T.G. Lucas, R.P. Rassool
    The University of Melbourne, Melbourne, Victoria, Australia
  • N. Catalán Lasheras, A. Grudiev, G. McMonagle, I. Syratchev, B.J. Woolley, W. Wuensch, V. del Pozo Romano
    CERN, Geneva, Switzerland
  • J. Paszkiewicz
    University of Oxford, Oxford, United Kingdom
  • C. Serpico
    Elettra-Sincrotrone Trieste S.C.p.A., Basovizza, Italy
  • A. Vnuchenko
    IFIC, Valencia, Spain
 
  In July 2016, the first X-band test facility operating with two interwoven, 6 MW klystron pulses was commissioned at CERN. Outputting up to 46 MW after pulse compression, the new test stand allows testing of two structures concurrently with repetition rates up to 400 Hz in each line. RF commissioning of all four lines has been completed and testing of high gradient accelerating structures for the Compact Linear Collider has commenced. Operations have been ongoing for more than a year, where dedicated control algorithms have been developed to conditioning the structure and to keep the pulse compressors tuned. Significant progress has been made in understanding the conditioning of two structures that are sharing an interlock and vacuum system. The high repetition rate is already showing the significantly reduced time needed to condition accelerating structures.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPMK104  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPML032 Using Deep Reinforcement Learning for Designing Sub-Relativistic Electron Linac electron, linac, cavity, acceleration 4720
 
  • Shin, S.W. Shin, J.-S. Chai, M. Ghergherehchi
    SKKU, Suwon, Republic of Korea
 
  Generally, when designing an accelerator device, the design is based on the experience and knowledge of the designer. Most of the design process proceeds by chang-ing the parameters and looking at the trends and then determining the optimal values. This process is time-consuming and tedious. In order to efficiently perform this tedious design process, a method using an optimization algorithm is used. Recently, many people started to get interested in the algorithm used in AlphaGo, which became famous when it won the professional Go player developed by google The algorithm used in AlphaGo is an algorithm called reinforcement learning that learns how to get optimal reward in various states by moving around a solution space that the agent has not told beforehand. In this paper, we will discuss about designing an particle accelerator by applying Deep Q-network algorithm which is one kind of deep learning reinforcement learning.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPML032  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPML069 The Control System Design of SCLF controls, interface, data-acquisition, software 4800
 
  • Y.B. Yan, J.G. Ding, G.Y. Jiang, Y.B. Leng
    SSRF, Shanghai, People's Republic of China
  • J.F. Chen
    SINAP, Shanghai, People's Republic of China
 
  The high-gain free electron lasers have given scientists hopes for new scientific discoveries in many frontier research areas. The Shanghai Coherent Light Facility (SCLF) was proposed by the central government of China on April 2017, which is a quasi-continuous wave hard X-ray free electron laser facility. The control system is responsible for the facility-wide device control, data acquisition, machine protection, high level database or application, as well as network and computing platform. It will be mainly based on EPICS to reach the balance between the high performance and costs of maintenance. The latest technology will be adopted for the high repetition rate data acquisition and feedback system. The details of the control system design will be reported in this paper.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPML069  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPML085 Intelligent Controls for the Electron Storage Ring DELTA controls, storage-ring, electron, synchrotron 4855
 
  • D. Schirmer
    DELTA, Dortmund, Germany
 
  In recent years, artificial intelligence has become one of the buzzwords in the field of controlling, monitoring and optimizing complex machines. Particle accelerators belong to this class of machines in particular. In accelerator controls one has to deal with a variety of time-varying parameters, nonlinear dynamics as well as a lot of small, compounding errors. Therefore, to cope with these tasks and to achieve higher performance, particle accelerators require new advanced strategies in controls and feedback systems. Machine learning through (deep) neural networks, genetic algorithms, swarm intelligence and adaptive controls are some of the proposed approaches. Increased computational capability and the availability of large data sets in combination with better theoretical understanding of new network architectures and training paradigms allow for promising approaches for novel developments. This report aims to discuss the state of the art techniques and presents ideas for possible applications of intelligent controls at the synchrotron radiation source DELTA.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPML085  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPML108 Distributed I/O System Based on Ethernet POWERLINK Under the EPICS Architecture EPICS, Ethernet, distributed, FPGA 4917
 
  • X.K. Sun, G. Liu, Y. Song
    USTC/NSRL, Hefei, Anhui, People's Republic of China
 
  Ethernet POWERLINK (EPL) is a communication profile for Real-Time Ethernet. The communication profile meets real-time demands for the distributed system composed of multiple controllers. EPICS is a wildly used distributed control system in large scientific facilities. We design a distributed IO system based on EPL under the EPICS architecture and establish the prototype system composed of a PC and six FPGA boards. In this system, an EPICS driver based on openPOWERLINK is developed to monitor the system status. In this paper, the communication mechanism of EPL, the design of system architecture, the implementation of EPICS driver and the test results of prototype system will be described.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPML108  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPML110 EPICS Driver for Siemens CP1616 Communication Module EPICS, real-time, controls, hardware 4923
 
  • Z. Huang, G. Liu, Y. Song, X.K. Sun
    USTC/NSRL, Hefei, Anhui, People's Republic of China
 
  Funding: Work supported by National Natural Science Foundation of China (11375186)
Siemens communication module CP1616 is a high-performance PROFINET controller, which can support both Real-time (RT) and Isochronous Real-Time (IRT) communication. Experimental Physics and Industrial Control System (EPICS) is a wildly used distributed control system in large scientific devices. In order to integrate PROFINET protocol into EPICS environment, we developed this driver based on CP1616 and established the prototype system. This paper will describe the design of EPICS driver for CP1616 and the test result of the prototype system.
 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPML110  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPML127 Alignment and Installation for the FELiChEM project alignment, FEL, laser, controls 4977
 
  • W. Wang, Zhang, H.T. H.T, X.Y. He, D.R. Xu
    USTC/NSRL, Hefei, Anhui, People's Republic of China
 
  Funding: Work supported by National Natural Science Foundation of China (11705199) and China Postdoctoral Science Foundation (2017M622024)
FELiChEM is a new experimental facility under construction at the University of Science and Technology of China. There are more than one hundred important devices to construct it, which core device is two free electron laser oscillators generating middle-infrared and far-infrared laser and covering the spectral range of 25-200μm. The optical cavity is an important component of oscillator which very sensitive to misalignment errors of the mirror, due to its near-concentric and symmetric structure. High precision alignment and installation is necessary to ensure the smooth implementation of the FELiChEM project. Laser tracker and Level are used to install this devices according to the alignment control network. An efficient and high-precision alignment method based on autocollimator and photoelectric auto-collimator is used to align optical cavity of oscillator. This methods is proven to be effective and meet the tolerances by multiple means.
 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPML127  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)