Keyword: network
Paper Title Other Keywords Page
MOPOST001 Performance of Automated Synchrotron Lattice Optimisation Using Genetic Algorithm lattice, dipole, synchrotron, focusing 38
 
  • X. Zhang, S.L. Sheehy
    The University of Melbourne, Melbourne, Victoria, Australia
  • S.L. Sheehy
    ANSTO, Kirrawee DC New South Wales, Australia
  
  Funding: Work supported by Australian Government Research Training Program Scholarship
Rapid ad­vances in su­per­con­duct­ing mag­nets and re­lated ac­cel­er­a­tor tech­nol­ogy opens many un­ex­plored pos­si­bil­i­ties for fu­ture syn­chro­tron de­signs. We pre­sent an ef­fi­cient method to probe the fea­si­ble pa­ra­me­ter space of syn­chro­tron lat­tice con­fig­u­ra­tions. Using this method, we can con­verge on a suite of op­ti­mal so­lu­tions with mul­ti­ple op­ti­mi­sa­tion ob­jec­tives. It is a gen­eral method that can be adapted to other lat­tice de­sign prob­lems with dif­fer­ent con­straints or op­ti­mi­sa­tion ob­jec­tives. In this method, we tackle the lat­tice de­sign prob­lem using a multi-ob­jec­tive ge­netic al­go­rithm. The prob­lem is en­coded by rep­re­sent­ing the com­po­nents of each lat­tice as columns of a ma­trix. This new method is an im­prove­ment over the neural net­work based ap­proach* in terms of com­pu­ta­tional re­sources. We eval­u­ate the per­for­mance and lim­i­ta­tions of this new method with bench­mark re­sults.
*Conference Proceedings IPAC’21, 2021. DOI:10.18429/JACoW-IPAC2021-MOPAB182 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOST001  
About • Received ※ 19 May 2022 — Revised ※ 13 June 2022 — Accepted ※ 14 June 2022 — Issue date ※ 17 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
MOPOPT002 Improvements on Sirius Beam Stability controls, operation, feedback, experiment 226
 
  • S.R. Marques, M.B. Alves, F.C. Arroyo, M.P. Calcanha, H.F. Canova, B.E. Limeira, L. Liu, R.T. Neuenschwander, A.G.C. Pereira, D.O. Tavares, F.H. de Sá
    LNLS, Campinas, Brazil
  • G.O. Brunheira, A.C.T. Cardoso, R.B. Cardoso, R. Junqueira Leão, L.R. Leão, P.H.S. Martins, Moreira, S.S. Moreira, R. Oliveira Neto, M.G. Siqueira
    CNPEM, Campinas, SP, Brazil
  
  Sir­ius is a Syn­chro­tron Light Source based on a 3 GeV elec­tron stor­age ring with 518 me­ters cir­cum­fer­ence and 250 pm.​rad emit­tance. The fa­cil­ity is built and op­er­ated by the Brazil­ian Syn­chro­tron Light Lab­o­ra­tory (LNLS), lo­cated in the CNPEM cam­pus, in Camp­inas. A beam sta­bil­ity task force was re­cently cre­ated to iden­tify and mit­i­gate the orbit dis­tur­bances at var­i­ous time scales. This work pre­sents stud­ies re­gard­ing ground mo­tion (land sub­si­dence caused by ground­wa­ter ex­trac­tion), im­prove­ments in the tem­per­a­ture con­trol of the stor­age ring (SR) tun­nel air con­di­tion­ing (AC) sys­tem, vi­bra­tion mea­sure­ments in ac­cel­er­a­tor com­po­nents and the ef­forts con­cern­ing the re­duc­tion of the power sup­plies’ rip­ple. The fast orbit feed­back im­ple­men­ta­tion and other fu­ture per­spec­tives will also be dis­cussed.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOPT002  
About • Received ※ 08 June 2022 — Revised ※ 14 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 17 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
MOPOPT041 Artificial Intelligence-Assisted Beam Distribution Imaging Using a Single Multimode Fiber at CERN experiment, simulation, coupling, detector 339
 
  • G. Trad, S. Burger
    CERN, Meyrin, Switzerland
  
  In the frame­work of de­vel­op­ing ra­di­a­tion tol­er­ant imag­ing de­tec­tors for trans­verse beam di­ag­nos­tics, the use of ma­chine learn­ing pow­ered imag­ing using op­ti­cal fibers is ex­plored for the first time at CERN. This paper pre­sents the pi­o­neer­ing work of using neural net­works to re­con­struct the scin­til­lat­ing screen beam image trans­ported from a harsh ra­dioac­tive en­vi­ron­ment over a sin­gle, large-core, mul­ti­mode, op­ti­cal fiber. Prof­it­ing from gen­er­a­tive mod­el­ing used in im­age-to-im­age trans­la­tion, con­di­tional ad­ver­sar­ial net­works have been trained to trans­late the out­put plane of the fiber, im­aged on a CMOS cam­era, into the beam image im­printed on the scin­til­lat­ing screen. The­o­ret­i­cal as­pects, cov­er­ing the de­vel­op­ment of the dataset via geo­met­ric op­tics sim­u­la­tions, mod­el­ing the image prop­a­ga­tion in a sim­pli­fied model of an op­ti­cal fiber, and its use for train­ing the net­work are dis­cussed. Fi­nally, the ex­per­i­men­tal se­tups, both in the lab­o­ra­tory and at the CLEAR fa­cil­ity at CERN, used to val­i­date the tech­nique and eval­u­ate its po­ten­tial are high­lighted.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOPT041  
About • Received ※ 08 June 2022 — Revised ※ 14 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 19 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
MOPOPT057 Updates in Efforts to Data Science Enabled MeV Ultrafast Electron Diffraction System electron, gun, laser, experiment 397
 
  • S. Biedron, T.B. Bolin, M. Martínez-Ramón, S.I. Sosa Guitron
    UNM-ECE, Albuquerque, USA
  • M. Babzien, M.G. Fedurin, J.J. Li, M.A. Palmer
    BNL, Upton, New York, USA
  • S. Biedron
    UNM-ME, Albuquerque, New Mexico, USA
  • D. Martin, M.E. Papka
    ANL, Lemont, Illinois, USA
  
  Funding: Work supported by DOEs EPSCoR award DE-SC0021365, used resources of the Brookhaven National Laboratory’s Accelerator Test Facility and of the Argonne Leadership Computing Facility.
MeV ul­tra­fast elec­tron dif­frac­tion (MUED) is a pump-probe char­ac­ter­i­za­tion tech­nique to study ul­tra­fast phe­nom­ena in ma­te­ri­als with high tem­po­ral and spa­tial res­o­lu­tion. This com­plex in­stru­ment can be ad­vanced into a turn-key, high-through­put tool with the aid of ma­chine learn­ing (ML) mech­a­nisms and high-per­for­mance com­put­ing. The MUED in­stru­ment at the Ac­cel­er­a­tor Test Fa­cil­ity in Brookhaven Na­tional Lab­o­ra­tory was em­ployed to test dif­fer­ent ML ap­proaches for both data analy­sis and con­trol. We char­ac­ter­ized dif­fer­ent ma­te­ri­als using MUED, mainly poly­crys­talline gold and sin­gle crys­tal Ta2NiS5. Dif­frac­tion pat­terns were ac­quired in sin­gle shot mode and con­vo­lu­tional neural net­work au­toen­con­der mod­els were eval­u­ated for noise re­duc­tion and the re­con­struc­tion error was stud­ied to iden­tify anom­alous dif­frac­tion pat­terns. Elec­tron beam en­ergy jit­ter was an­a­lyzed from sin­gle shot dif­frac­tion pat­terns to be used as a novel di­ag­nos­tic tool. The MUED beam­line was also sim­u­lated using VSim to con­struct a sur­ro­gate model for con­trol of beam shape and en­ergy. Progress to­wards ML-based con­trols lever­ag­ing off Ar­gonne Lead­er­ship Com­put­ing Fa­cil­ity re­sources will also be pre­sented. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOPT057  
About • Received ※ 02 July 2022 — Accepted ※ 26 June 2022 — Issue date ※ 08 July 2022  
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
MOPOPT067 Electron Beam Phase Space Reconstruction From a Gas Sheet Diagnostic simulation, electron, diagnostics, experiment 414
 
  • N.M. Cook, A. Diaw, C.C. Hall
    RadiaSoft LLC, Boulder, Colorado, USA
  • G. Andonian
    RadiaBeam, Santa Monica, California, USA
  • N.P. Norvell
    UCSC, Santa Cruz, California, USA
  • M. Yadav
    The University of Liverpool, Liverpool, United Kingdom
  
  Funding: This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of High Energy Physics under Award Number DE-SC0019717.
Next gen­er­a­tion par­ti­cle ac­cel­er­a­tors craft in­creas­ingly high bright­ness beams to achieve physics goals for ap­pli­ca­tions rang­ing from col­lid­ers to free elec­tron lasers to stud­ies of non­per­tur­ba­tive QED. Such rig­or­ous re­quire­ments on total charge and shape in­tro­duce di­ag­nos­tic chal­lenges for ef­fec­tively mea­sur­ing bunch pa­ra­me­ters prior to or at in­ter­ac­tion points. We re­port on the sim­u­la­tion and train­ing of a non-de­struc­tive beam di­ag­nos­tic ca­pa­ble of char­ac­ter­iz­ing high in­ten­sity charged par­ti­cle beams. The di­ag­nos­tic con­sists of a tai­lored neu­tral gas cur­tain, elec­tro­sta­tic mi­cro­scope, and high sen­si­tiv­ity cam­era. An in­ci­dent elec­tron beam ion­izes the gas cur­tain, while the elec­tro­sta­tic mi­cro­scope trans­ports gen­er­ated ions to an imag­ing screen. Sim­u­la­tions of the ion­iza­tion and trans­port process are per­formed using the Warp code. Then, a neural net­work is trained to pro­vide ac­cu­rate es­ti­mates of the ini­tial elec­tron beam pa­ra­me­ters. We pre­sent ini­tial re­sults for a range of beam and gas cur­tain pa­ra­me­ters and com­ment on ex­ten­si­bil­ity to other beam in­ten­sity regimes.

 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOPT067  
About • Received ※ 08 June 2022 — Accepted ※ 17 June 2022 — Issue date ※ 10 July 2022  
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
MOPOTK038 BPM Analysis with Variational Autoencoders focusing, diagnostics, GPU, optics 543
 
  • C.C. Hall, J.P. Edelen, J.A. Einstein-Curtis, M.C. Kilpatrick
    RadiaSoft LLC, Boulder, Colorado, USA
  
  Funding: This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of High Energy Physics under Award Number DE-SC0021699.
In par­ti­cle ac­cel­er­a­tors, beam po­si­tion mon­i­tors (BPMs) are used ex­ten­sively as a non-in­ter­cept­ing di­ag­nos­tic. Sig­nif­i­cant in­for­ma­tion about beam dy­nam­ics can often be ex­tracted from BPM mea­sure­ments and used to ac­tively tune the ac­cel­er­a­tor. How­ever, com­mon mea­sure­ment tools, such as mea­sure­ments of kicked beams, may be­come more dif­fi­cult when very strong non­lin­ear­i­ties are pre­sent or when data is very noisy. In this work, we ex­am­ine the use of vari­a­tional au­toen­coders (VAEs) as a tech­nique to ex­tract mea­sure­ments of the beam from sim­u­lated turn-by-turn BPM data. In par­tic­u­lar, we show that VAEs may have the pos­si­bil­ity to out­per­form other di­men­sion­al­ity re­duc­tion tech­niques that have his­tor­i­cally been used to an­a­lyze such data. When the data col­lec­tion pe­riod is lim­ited, or the data is noisy, VAEs may offer sig­nif­i­cant ad­van­tages. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOTK038  
About • Received ※ 09 June 2022 — Revised ※ 13 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 10 July 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUOXGD2 Wireless IoT in Particle Accelerators: A Proof of Concept with the IoT Radiation Monitor at CERN radiation, monitoring, electron, electronics 772
 
  • S. Danzeca, A.J. Cass, A. Masi, R. Sierra, A. Zimmaro
    CERN, Meyrin, Switzerland
  
  The In­ter­net of Things (IoT) is an ecosys­tem of web-en­abled "smart de­vices" that in­te­grates sen­sors and com­mu­ni­ca­tion hard­ware to col­lect, send and act on data ac­quired from the sur­round­ing en­vi­ron­ment. Use of the IoT in par­ti­cle ac­cel­er­a­tors is not new, with ac­cel­er­a­tor sys­tems long hav­ing been con­nected to the net­work to re­trieve, send and analyse data. What has been miss­ing is the IoT con­cept of "smart de­vices" and above all wire­less con­nec­tiv­ity. We re­port here on the ad­van­tages of using a par­tic­u­lar IoT tech­nol­ogy, LoRa, for the de­ploy­ment of wire­less ra­di­a­tion mon­i­tors within the CERN par­ti­cle ac­cel­er­a­tor com­plex. IoT Ra­di­a­tion Mon­i­tors have been de­vel­oped as a re­sult of grow­ing de­mand for ra­di­a­tion mea­sure­ments where stan­dard in­fra­struc­ture is not avail­able. As a ra­di­a­tion-tol­er­ant de­vice, the IoT Ra­di­a­tion Mon­i­tor is a pow­er­ful "eye" for ob­serv­ing the real-time ra­di­a­tion lev­els in the CERN ac­cel­er­a­tors. We de­scribe here the tech­nolo­gies used for the pro­ject and the var­i­ous ad­van­tages their de­ploy­ment of­fers in a par­ti­cle ac­cel­er­a­tor en­vi­ron­ment. This opens up the pos­si­bil­ity for the de­ploy­ment of het­ero­ge­neous im­ple­men­ta­tions that would oth­er­wise have been im­prac­ti­cal.  
slides icon Slides TUOXGD2 [5.797 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUOXGD2  
About • Received ※ 07 June 2022 — Revised ※ 11 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 17 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUOXGD3 6D Phase Space Diagnostics Based on Adaptively Tuned Physics-Informed Generative Convolutional Neural Networks controls, feedback, solenoid, diagnostics 776
 
  • A. Scheinker
    LANL, Los Alamos, New Mexico, USA
  • F.W. Cropp V
    UCLA, Los Angeles, USA
  • D. Filippetto
    LBNL, Berkeley, California, USA
  
  Funding: US Department of Energy, DOE Office of Science Graduate Student Research (SCGSR) contract numbers 89233218CNA000001 and DE-AC02-05CH11231 and by the NSF under Grant No. PHY-1549132.
A physics-in­formed gen­er­a­tive con­vo­lu­tional neural net­work (CNN)-based 6D phase space di­ag­nos­tic is pre­sented which gen­er­ates all 15 unique 2D pro­jec­tions (x,y), (x,y’),…, (z,E) of a charged par­ti­cle beam’s 6D phase space (x,y,z,x’,y’,E)*. The CNN is trained by su­per­vised learn­ing over a wide range of input beam dis­tri­b­u­tions, ac­cel­er­a­tor pa­ra­me­ters, and the as­so­ci­ated 6D beam phase spaces at mul­ti­ple ac­cel­er­a­tor lo­ca­tions. The CNN is ap­plied in an un-su­per­vised adap­tive man­ner with­out knowl­edge of the input beam dis­tri­b­u­tion or ac­cel­er­a­tor pa­ra­me­ters and is ro­bust to their un­known time vari­a­tion. Adap­tive feed­back au­to­mat­i­cally tunes the low-di­men­sional la­tent space of the en­coder-de­coder CNN to pre­dict the 6D phase space based only on 2D (z,E) lon­gi­tu­di­nal phase space mea­sure­ments from a de­vice such as a trans­verse de­flect­ing RF cav­ity (TCAV). This method has the po­ten­tial to pro­vide di­ag­nos­tics be­yond the ex­ist­ing state of the art at many ac­cel­er­a­tor fa­cil­i­ties. Stud­ies are pre­sented for two very dif­fer­ent ac­cel­er­a­tors: the 5-me­ter-long ul­tra-fast elec­tron dif­frac­tion (UED) HiRES com­pact ac­cel­er­a­tor at LBNL and the kilo­me­ter long plasma wake­field ac­cel­er­a­tor FACET-II at SLAC.
*A. Scheinker. "Adaptive machine learning for time-varying systems: low dimensional latent space tuning." Journal of Instrumentation 16.10, 2021: P10008. https://doi.org/10.1088/1748-0221/16/10/P10008 		 
slides icon Slides TUOXGD3 [3.112 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUOXGD3  
About • Received ※ 21 May 2022 — Revised ※ 13 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 16 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOST009 Online Correction of Laser Focal Position Using FPGA-Based ML Models laser, FPGA, controls, electron 857
 
  • J.A. Einstein-Curtis, S.J. Coleman, N.M. Cook, J.P. Edelen
    RadiaSoft LLC, Boulder, Colorado, USA
  • S.K. Barber, C.E. Berger, J. van Tilborg
    LBNL, Berkeley, California, USA
  
  Funding: This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of High Energy Physics under Award Numbers DE-SC 00259037 and DE-AC02-05CH11231.
High rep­e­ti­tion-rate, ul­tra­fast laser sys­tems play a crit­i­cal role in a host of mod­ern sci­en­tific and in­dus­trial ap­pli­ca­tions. We pre­sent a pro­to­type di­ag­nos­tic and cor­rec­tion scheme for con­trol­ling and de­ter­min­ing laser focal po­si­tion at 10 s of Hz rate by uti­liz­ing fast wave­front sen­sor mea­sure­ments from mul­ti­ple po­si­tions to train a focal po­si­tion pre­dic­tor. This pre­dic­tor is used to de­ter­mine cor­rec­tions for ac­tu­a­tors along the beam­line to pro­vide the de­sired cor­rec­tion to the focal po­si­tion on mil­lisec­ond timescales. Our ini­tial proof-of-prin­ci­ple demon­stra­tions lever­age pre-com­piled data and pre-trained net­works op­er­at­ing ex-situ from the laser sys­tem. We then dis­cuss the ap­pli­ca­tion of a high-level syn­the­sis frame­work for gen­er­at­ing a low-level hard­ware de­scrip­tion of ML-based cor­rec­tion al­go­rithms on FPGA hard­ware cou­pled di­rectly to the beam­line. Lastly, we con­sider the use of re­mote com­put­ing re­sources, such as the Sirepo sci­en­tific frame­work* , to ac­tively up­date these cor­rec­tion schemes and de­ploy mod­els to a pro­duc­tion en­vi­ron­ment.
* M.S. Rakitin et al., "Sirepo: an open-source cloud-based software interface for X-ray source and optics simulations", Journal of Synchrotron Radiation 25, 1877-1892 (Nov 2018). 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST009  
About • Received ※ 20 May 2022 — Revised ※ 14 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 23 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOST015 Commissioning and First Results of an X-Band LLRF System for TEX Test Facility at LNF-INFN LLRF, MMI, klystron, GUI 876
 
  • L. Piersanti, D. Alesini, M. Bellaveglia, S. Bini, B. Buonomo, F. Cardelli, C. Di Giulio, E. Di Pasquale, M. Diomede, L. Faillace, A. Falone, G. Franzini, A. Gallo, G. Giannetti, A. Liedl, D. Moriggi, S. Pioli, S. Quaglia, L. Sabbatini, M. Scampati, G. Scarselletta, A. Stella, S. Tocci, L. Zelinotti
    LNF-INFN, Frascati, Italy
  
  Funding: Latino is a project co-funded by Regione Lazio within POR-FESR 2014-2020 program
In the frame­work of LATINO pro­ject (Lab­o­ra­tory in Ad­vanced Tech­nolo­gies for IN­nO­va­tion) funded by Lazio re­gional gov­ern­ment, the com­mis­sion­ing of the TEst stand for X-band (TEX) fa­cil­ity has started in 2021 at Fras­cati Na­tional Lab­o­ra­to­ries of INFN. Born as a col­lab­o­ra­tion with CERN to test high gra­di­ent ac­cel­er­at­ing struc­tures, dur­ing 2022 TEX aims at feed­ing the first EuPRAXIA@​SPARC_​LAB X-band struc­ture pro­to­type. Dur­ing 2021 the com­mis­sion­ing has been suc­cess­fully car­ried out up to 48 MW. The power unit is dri­ven by an X-band low level RF sys­tem, that em­ploys a com­mer­cial S-band (2.856 GHz) Lib­era dig­i­tal LLRF (man­u­fac­tured by In­stru­men­ta­tion Tech­nolo­gies), with an up/down con­ver­sion stage and a ref­er­ence gen­er­a­tion and dis­tri­b­u­tion sys­tem able to pro­duce co­her­ent fre­quen­cies for the Amer­i­can S-band and Eu­ro­pean X-band (11.994 GHz), both de­signed and re­al­ized at LNF. The per­for­mance of the sys­tem, with a par­tic­u­lar focus on am­pli­tude and phase res­o­lu­tion, to­gether with kly­stron and dri­ver am­pli­fier jit­ter mea­sure­ments, will be re­viewed in this paper. More­over, con­sid­er­a­tions on its suit­abil­ity and main lim­i­ta­tions in view of EuPRAXIA@​SPARC_​LAB pro­ject will be dis­cussed. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST015  
About • Received ※ 20 May 2022 — Revised ※ 13 June 2022 — Accepted ※ 17 June 2022 — Issue date ※ 28 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOST043 A Novel Method for Detecting Unidentified Falling Object Loss Patterns in the LHC operation, Windows, ECR, machine-protect 953
 
  • L. Coyle, F. Blanc, D. Di Croce, T. Pieloni
    EPFL, Lausanne, Switzerland
  • L. Coyle, A. Lechner, D. Mirarchi, M. Solfaroli Camillocci, J. Wenninger
    CERN, Meyrin, Switzerland
  
  Un­der­stand­ing and mit­i­gat­ing par­ti­cle losses in the Large Hadron Col­lider (LHC) is es­sen­tial for both ma­chine safety and ef­fi­cient op­er­a­tion. Ab­nor­mal loss dis­tri­b­u­tions are tell­tale signs of ab­nor­mal beam be­hav­iour or in­cor­rect ma­chine con­fig­u­ra­tion. By lever­ag­ing the ad­vance­ments made in the field of Ma­chine Learn­ing, a novel data-dri­ven method of de­tect­ing anom­alous loss dis­tri­b­u­tions dur­ing ma­chine op­er­a­tion has been de­vel­oped. A neural net­work anom­aly de­tec­tion model was trained to de­tect Uniden­ti­fied Falling Ob­ject events using sta­ble beam, Beam Loss Mon­i­tor (BLM) data ac­quired dur­ing the op­er­a­tion of the LHC. Data-dri­ven mod­els, such as the one pre­sented, could lead to sig­nif­i­cant im­prove­ments in the au­tonomous la­belling of ab­nor­mal loss dis­tri­b­u­tions, ul­ti­mately bol­ster­ing the ever on­go­ing ef­fort to­ward im­prov­ing the un­der­stand­ing and mit­i­ga­tion of these events.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST043  
About • Received ※ 19 May 2022 — Revised ※ 15 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 21 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOST044 Fortune Telling or Physics Prediction? Deep Learning for On-Line Kicker Temperature Forecasting kicker, operation, simulation, injection 957
 
  • F.M. Velotti, M.J. Barnes, B. Goddard, I. Revuelta
    CERN, Meyrin, Switzerland
  
  The in­jec­tion kicker sys­tem MKP of the Super Pro­ton Syn­chro­tron SPS at CERN is com­posed of 4 kicker tanks. The MKP-L tank pro­vides ad­di­tional kick needed to in­ject 26 GeV Large Hadron Col­lider LHC 25 ns type beams. This de­vice has been a lim­it­ing fac­tor for op­er­a­tion with high in­ten­sity, due to the mag­net’s broad­band beam cou­pling im­ped­ance and con­se­quent beam in­duced heat­ing. To op­ti­mise the usage of the SPS and avoid idle (kicker cool­ing) time, stud­ies were con­ducted to de­velop a re­cur­rent deep learn­ing model that could pre­dict the mea­sured tem­per­a­ture evo­lu­tion of the MKP-L, using the beam con­di­tions and tem­per­a­ture his­tory as input. In a sec­ond stage, the fer­rite tem­per­a­ture is also es­ti­mated putting to­gether the ex­ter­nal tem­per­a­ture pre­dic­tions from ac­cu­rate thermo-me­chan­i­cal sim­u­la­tions of the kicker mag­net. In this paper, the method­ol­ogy is de­scribed and de­tails of the neural net­work ar­chi­tec­ture used, to­gether with the im­ple­men­ta­tion of an ad-hoc loss func­tion, are given. The re­sults ap­plied to the SPS 2021 op­er­a­tional data are pre­sented.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST044  
About • Received ※ 06 June 2022 — Revised ※ 14 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 18 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOST050 Liverpool Centre for Doctoral Training for Innovation in Data Intensive Science cathode, simulation, experiment, electron 976
 
  • C.P. Welsch
    Cockcroft Institute, Warrington, Cheshire, United Kingdom
  • C.P. Welsch
    The University of Liverpool, Liverpool, United Kingdom
  
  Funding: This new Center for Doctoral Training has received funding from the UK’s Science and Technology Facilities Council.
The Liv­er­pool cen­ter for doc­toral train­ing for in­no­va­tion in data in­ten­sive sci­ence (LIV. INNO) is an in­clu­sive hub for train­ing three co­horts of stu­dents in data in­ten­sive sci­ence. Start­ing in Oc­to­ber 2022, each year will train about 12 PhD stu­dents in ap­ply­ing data skills to ad­dress cut­ting edge re­search chal­lenges across as­tro­physics, nu­clear, the­o­ret­i­cal and par­ti­cle physics, as well as ac­cel­er­a­tor sci­ence. This frame­work is ex­pected to pro­vide an ideal basis for dri­ving sci­ence and in­no­va­tion, as well as boost­ing the em­ploy­a­bil­ity of the LIV. INNO PhD stu­dents. This con­tri­bu­tion gives ex­am­ples of the ac­cel­er­a­tor sci­ence R&D pro­jects in the cen­ter. It in­cludes de­tails about re­search into the op­ti­miza­tion of 3D imag­ing tech­niques and the char­ac­ter­i­za­tion of pho­to­cath­odes for ac­cel­er­a­tor ap­pli­ca­tions. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST050  
About • Received ※ 05 June 2022 — Revised ※ 09 June 2022 — Accepted ※ 17 June 2022 — Issue date ※ 06 July 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOPT013 Twin Delayed Deep Deterministic Policy Gradient for Free-electron Laser Online Optimization FEL, electron, laser, undulator 1025
 
  • M. Cai, C. Feng, L. Tu, Z.T. Zhao, Z.H. Zhu
    SINAP, Shanghai, People’s Republic of China
  • C. Feng, K.Q. Zhang, Z.T. Zhao
    SSRF, Shanghai, People’s Republic of China
  • D. Gu
    SARI-CAS, Pudong, Shanghai, People’s Republic of China
  
  X-ray free-elec­tron lasers (FEL) have con­tributed to many fron­tier ap­pli­ca­tions of nanoscale sci­ence which ben­e­fit from its ex­tra­or­di­nary prop­er­ties. Dur­ing FEL com­mis­sion­ing, the beam sta­tus op­ti­miza­tion es­pe­cially orbit cor­rec­tion is par­tic­u­larly sig­nif­i­cant for FEL am­pli­fi­ca­tion. For ex­am­ple, the de­vi­a­tion be­tween beam orbit and the mag­netic cen­ter of un­du­la­tor can af­fect the in­ter­ac­tion be­tween the elec­tron beam and the FEL pulse. Usu­ally, FEL com­mis­sion­ing re­quires a lot of ef­fort for multi-di­men­sional pa­ra­me­ters op­ti­miza­tion in a time-vary­ing sys­tem. There­fore, ad­vanced al­go­rithms are needed to fa­cil­i­tate the com­mis­sion­ing pro­ce­dure. In this paper, we pro­pose an on­line method to op­ti­mize the FEL power and trans­verse co­her­ence by using a twin de­layed deep de­ter­min­is­tic pol­icy gra­di­ent (TD3) al­go­rithm. The al­go­rithm ex­hibits more sta­ble learn­ing con­ver­gence and im­proves learn­ing per­for­mance be­cause the over­es­ti­ma­tion bias of pol­icy gra­di­ent meth­ods is sup­pressed.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOPT013  
About • Received ※ 17 May 2022 — Revised ※ 14 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 22 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOPT058 A Machine Learning Approach to Electron Orbit Control at the 1.5 GeV Synchrotron Light Source DELTA storage-ring, synchrotron, controls, electron 1137
 
  • D. Schirmer
    DELTA, Dortmund, Germany
  
  Ma­chine learn­ing (ML) meth­ods have found their ap­pli­ca­tion in a wide range of par­ti­cle ac­cel­er­a­tor con­trol tasks. Among other pos­si­ble use cases, neural net­works (NNs) can also be uti­lized for au­to­mated beam po­si­tion con­trol (orbit cor­rec­tion). ML stud­ies on this topic, which were ini­tially based on sim­u­la­tions, were suc­cess­fully trans­ferred to real ac­cel­er­a­tor op­er­a­tion at the 1.5-GeV elec­tron stor­age ring of the DELTA ac­cel­er­a­tor fa­cil­ity. For this pur­pose, clas­si­cal fully con­nected multi-layer feed-for­ward NNs were trained by su­per­vised learn­ing on mea­sured orbit data to apply local and global beam po­si­tion cor­rec­tions. The su­per­vised NN train­ing was car­ried out with var­i­ous con­ju­gate gra­di­ent back­prop­a­ga­tion learn­ing al­go­rithms. Af­ter­wards, the ML-based orbit cor­rec­tion per­for­mance was com­pared with a con­ven­tional, nu­mer­i­cal-based com­put­ing method. Here, the ML-based ap­proach showed a com­pet­i­tive orbit cor­rec­tion qual­ity in a fewer num­ber of cor­rec­tion steps.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOPT058  
About • Received ※ 20 May 2022 — Accepted ※ 16 June 2022 — Issue date ※ 25 June 2022  
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOPT062 A Data-Driven Anomaly Detection on SRF Cavities at the European XFEL cavity, FEL, SRF, experiment 1152
 
  • A. Sulc, A. Eichler, T. Wilksen
    DESY, Hamburg, Germany
  
  Funding: This work was supported by HamburgX grant LFF-HHX-03 to the Center for Data and Computing in Natural Sciences (CDCS) from the Hamburg Ministry of Science, Research, Equalities and Districts.
The Eu­ro­pean XFEL is cur­rently op­er­at­ing with hun­dreds of su­per­con­duct­ing radio fre­quency cav­i­ties. To be able to min­i­mize the down­times, pre­ven­tion of fail­ures on the SRF cav­i­ties is cru­cial. In this paper, we pro­pose an anom­aly de­tec­tion ap­proach based on a neural net­work model to pre­dict oc­cur­rences of break­downs on the SRF cav­i­ties based on a model trained on his­tor­i­cal data. We used our ex­ist­ing anom­aly de­tec­tion in­fra­struc­ture to get a sub­set of the stored data la­beled as faulty. We ex­per­i­mented with dif­fer­ent train­ing losses to max­i­mally profit from the avail­able data and trained a re­cur­rent neural net­work that can pre­dict a fail­ure from a se­ries of pulses. The pro­posed model is using a tai­lored ar­chi­tec­ture with re­cur­rent neural units and takes into ac­count the se­quen­tial na­ture of the prob­lem which can gen­er­al­ize and pre­dict a va­ri­ety of fail­ures that we have been ex­pe­ri­enc­ing in op­er­a­tion. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOPT062  
About • Received ※ 17 May 2022 — Revised ※ 14 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 24 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOPT070 Surrogate Modelling of the FLUTE Low-Energy Section simulation, gun, electron, controls 1182
 
  • C. Xu, E. Bründermann, A.-S. Müller, A. Santamaria Garcia, J. Schäfer
    KIT, Karlsruhe, Germany
  
  Funding: Supported by the Helmholtz Association (Autonomous Accelerator, ZT-I-PF-5-6) and the DFG-funded Doctoral School "Karlsruhe School of Elementary and Astroparticle Physics: Science and Technology".
Nu­mer­i­cal beam dy­nam­ics sim­u­la­tions are es­sen­tial tools in the study and de­sign of par­ti­cle ac­cel­er­a­tors, but they can be pro­hib­i­tively slow for on­line pre­dic­tion dur­ing op­er­a­tion or for sys­tem­atic eval­u­a­tions of new pa­ra­me­ter set­tings. Ma­chine learn­ing-based sur­ro­gate mod­els of the ac­cel­er­a­tor pro­vide much faster pre­dic­tions of the beam prop­er­ties and can serve as a vir­tual di­ag­nos­tic or to aug­ment data for re­in­force­ment learn­ing train­ing. In this paper, we pre­sent the first re­sults on train­ing a sur­ro­gate model for the low-en­ergy sec­tion at the Fer­n­in­frarot Linac- und Test-Ex­per­i­ment (FLUTE). 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOPT070  
About • Received ※ 30 May 2022 — Accepted ※ 15 June 2022 — Issue date ※ 05 July 2022  
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOTK055 One Year of Operation of the New Wideband RF System of the Proton Synchrotron Booster MMI, operation, cavity, controls 1344
 
  • G.G. Gnemmi, S. Energico, M. Haase, M.M. Paoluzzi, C. Rossi
    CERN, Meyrin, Switzerland
  
  Within the LHC In­jec­tors Up­grade pro­ject, the PS Booster(PSB) has been up­graded. Both the in­jec­tion (160 MeV) and ex­trac­tion (2 GeV) en­er­gies have been in­creased, bring­ing also changes in the in­jec­tion beam rev­o­lu­tion fre­quency, the max­i­mum rev­o­lu­tion fre­quency, and the beam in­ten­sity. To meet the re­quire­ments of the High Lu­mi­nos­ity LHC a new RF sys­tem has been de­signed, based on the wide­band fre­quency char­ac­ter­is­tics of Finemet® Mag­netic Alloy and solid-state am­pli­fiers. The wide­band fre­quency re­sponse (1 MHz to 18 MHz) cov­ers all the re­quired fre­quency schemes in the PSB, al­low­ing multi-har­mon­ics op­er­a­tion. The sys­tem is based on a cel­lu­lar con­fig­u­ra­tion in which each cell pro­vides a frac­tion of the total RF volt­age. The new RF sys­tem has been in­stalled in 3 lo­ca­tions re­plac­ing the old sys­tems. The in­stal­la­tion has been per­formed dur­ing 2019/2020, while the com­mis­sion­ing started later in 2020 and rel­e­vant re­sults for the physics have been al­ready ob­served. This paper de­scribes the new RF chain, the re­sults achieved and the is­sues that oc­curred dur­ing this year of op­er­a­tion, to­gether with the changes made to the sys­tem to im­prove per­for­mance and re­li­a­bil­ity.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOTK055  
About • Received ※ 02 June 2022 — Revised ※ 14 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 28 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOTK061 Prospects to Apply Machine Learning to Optimize the Operation of the Crystal Collimation System at the LHC collimation, operation, collider, hadron 1362
 
  • M. D’Andrea, G. Azzopardi, M. Di Castro, E. Matheson, D. Mirarchi, S. Redaelli, G. Valentino
    CERN, Meyrin, Switzerland
  • G. Ricci
    Sapienza University of Rome, Rome, Italy
  
  Funding: Research supported by the HL-LHC project.
Crys­tal col­li­ma­tion re­lies on the use of bent crys­tals to co­her­ently de­flect halo par­ti­cles onto ded­i­cated col­li­ma­tor ab­sorbers. This scheme is planned to be used at the LHC to im­prove the be­ta­tron clean­ing ef­fi­ciency with high-in­ten­sity ion beams. Only par­ti­cles with im­ping­ing an­gles below 2.5 urad rel­a­tive to the crys­talline planes can be ef­fi­ciently chan­neled at the LHC nom­i­nal top en­ergy of 7 Z TeV. For this rea­son, crys­tals must be kept in op­ti­mal align­ment with re­spect to the cir­cu­lat­ing beam en­ve­lope to max­i­mize the ef­fi­ciency of the chan­nel­ing process. Given the small an­gu­lar ac­cep­tance, achiev­ing op­ti­mal chan­nel­ing con­di­tions is par­tic­u­larly chal­leng­ing. Fur­ther­more, the dif­fer­ent phases of the LHC op­er­a­tional cycle in­volve im­por­tant dy­namic changes of the local orbit and op­tics, re­quir­ing an op­ti­mized con­trol of po­si­tion and angle of the crys­tals rel­a­tive to the beam. To this end, the pos­si­bil­ity to apply ma­chine learn­ing to the align­ment of the crys­tals, in a ded­i­cated setup and in stan­dard op­er­a­tion, is con­sid­ered. In this paper, pos­si­ble so­lu­tions for au­to­matic adap­ta­tion to the chang­ing beam pa­ra­me­ters are high­lighted and plans for the LHC ion runs start­ing in 2022 are dis­cussed. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOTK061  
About • Received ※ 07 June 2022 — Revised ※ 12 June 2022 — Accepted ※ 21 June 2022 — Issue date ※ 24 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUPOMS054 Data Augmentation for Breakdown Prediction in CLIC RF Cavities operation, cavity, experiment, ECR 1553
 
  • H.S. Bovbjerg, M. Shen, Z.H. Tan
    Aalborg University, Aalborg, Denmark
  • A. Apollonio, H.S. Bovbjerg, T. Cartier-Michaud, W.L. Millar, C. Obermair, D. Wollmann
    CERN, Meyrin, Switzerland
  • C. Obermair
    TUG, Graz, Austria
  
  One of the pri­mary lim­i­ta­tions on the achiev­able ac­cel­er­at­ing gra­di­ent in nor­mal-con­duct­ing ac­cel­er­a­tor cav­i­ties is the oc­cur­rence of vac­uum arcs, also known as RF break­downs. A re­cent study on ex­per­i­men­tal data from the CLIC XBOX2 test stand at CERN pro­poses the use of su­per­vised ma­chine learn­ing meth­ods for pre­dict­ing RF break­downs. As RF break­downs occur rel­a­tively in­fre­quently dur­ing op­er­a­tion, the ma­jor­ity of the data was in­stead com­prised of non-break­down pulses. This phe­nom­e­non is known in the field of ma­chine learn­ing as class im­bal­ance and is prob­lem­atic for the train­ing of the mod­els. This paper pro­poses the use of data aug­men­ta­tion meth­ods to gen­er­ate syn­thetic data to coun­ter­act this prob­lem. Dif­fer­ent data aug­men­ta­tion meth­ods like ran­dom trans­for­ma­tions and pat­tern mix­ing are ap­plied to the ex­per­i­men­tal data from the XBOX2 test stand, and their ef­fi­ciency is com­pared.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOMS054  
About • Received ※ 08 June 2022 — Revised ※ 12 June 2022 — Accepted ※ 13 June 2022 — Issue date ※ 15 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEINGD1 Industry and Accelerator Science, Technology, and Engineering - the Need to Integrate (Building Bridges) electron, laser, radiation, MMI 1644
 
  • R. Geometrante
    KYMA, Trieste, Italy
  • S. Biedron
    Element Aero, Chicago, USA
  • E. Braidotti
    CAEN ELS srl, Trieste, Italy
  • J.M.A. Priem
    VDL ETG, Eindhoven, The Netherlands
  • J.C. Rugsancharoenphol
    FTI, Bangkok, Thailand
  • S.L. Sheehy
    The University of Melbourne, Melbourne, Victoria, Australia
  • M. Vretenar
    CERN, Meyrin, Switzerland
  
  Ab­stract  
slides icon Slides WEINGD1 [36.079 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-WEINGD1  
About • Received ※ 05 July 2022 — Accepted ※ 04 July 2022 — Issue date ※ 05 July 2022  
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
WEPOPT008 Supervised Machine Learning for Local Coupling Sources Detection in the LHC coupling, quadrupole, optics, simulation 1842
 
  • F. Soubelet, T.H.B. Persson, R. Tomás García
    CERN, Meyrin, Switzerland
  • Ö. Apsimon, C.P. Welsch
    Cockcroft Institute, Warrington, Cheshire, United Kingdom
  
  Funding: This research is supported by the LIV. DAT Center for Doctoral Training, STFC and the European Organization for Nuclear Research
Local in­ter­ac­tion re­gion (IR) lin­ear cou­pling in the LHC has been shown to have a neg­a­tive im­pact on beam size and lu­mi­nos­ity, mak­ing its ac­cu­rate cor­rec­tion for Run 3 and be­yond a ne­ces­sity. In view of de­ter­min­ing cor­rec­tions, su­per­vised ma­chine learn­ing has been ap­plied to the de­tec­tion of lin­ear cou­pling sources, show­ing promis­ing re­sults in sim­u­la­tions. An eval­u­a­tion of dif­fer­ent ap­plied mod­els is given, fol­lowed by the pre­sen­ta­tion of fur­ther pos­si­ble ap­pli­ca­tion con­cepts for lin­ear cou­pling cor­rec­tions using ma­chine learn­ing. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-WEPOPT008  
About • Received ※ 03 June 2022 — Revised ※ 15 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 29 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THIYGD1 White Rabbit Based Beam-Synchronous Timing Systems for SHINE timing, FEL, electron, FPGA 2415
 
  • Y.B. Yan, G.H. Chen, Q.W. Xiao, P.X. Yu
    SSRF, Shanghai, People’s Republic of China
  • G.H. Gong
    Tsinghua University, Beijing, People’s Republic of China
  • J.L. Gu, Z.Y. Jiang, L. Zhao
    USTC, Hefei, Anhui, People’s Republic of China
  • Y.M. Ye
    TUB, Beijing, People’s Republic of China
  
  Shang­hai HIgh rep­e­ti­tion rate XFEL aNd Ex­treme light fa­cil­ity (SHINE) is under con­struc­tion. SHINE re­quires pre­cise dis­tri­b­u­tion and syn­chro­niza­tion of the 1.003086 MHz tim­ing sig­nals over a long dis­tance of about 3.1 km. Two pro­to­type sys­tems were de­vel­oped, both con­tain­ing three func­tions: beam-syn­chro­nous trig­ger sig­nal dis­tri­b­u­tion, ran­dom-event trig­ger sig­nal dis­tri­b­u­tion and data ex­change be­tween nodes. The fre­quency of the beam-syn­chro­nous trig­ger sig­nal can be di­vided ac­cord­ing to the ac­cel­er­a­tor op­er­a­tion mode. Each out­put pulse can be con­fig­ured for dif­fer­ent fill modes. A pro­to­type sys­tem was de­signed based on a cus­tomized clock fre­quency point (64.197530 MHz). An­other pro­to­type sys­tem was de­signed based on the stan­dard White Rab­bit pro­to­col. The DDS (Di­rect Dig­i­tal Syn­the­sis) and D flip-flops (DFFs) are adopted for RF sig­nal trans­fer and pulse con­fig­u­ra­tion. The de­tails of the tim­ing sys­tem de­sign, lab­o­ra­tory test re­sults will be re­ported in this paper.  
slides icon Slides THIYGD1 [5.582 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-THIYGD1  
About • Received ※ 29 May 2022 — Revised ※ 10 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 17 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPOPT008 Beam Orbit Shift Due to BPM Thermal Deformation Using Machine Learning storage-ring, synchrotron, vacuum, feedback 2577
 
  • K.M. Chen, M. Hosaka, F.Y. Wang, G. Wang, Z. Wang, W. Xu
    USTC/NSRL, Hefei, Anhui, People’s Republic of China
  • L. Guo
    Nagoya University, Nagoya, Japan
  
  Sta­bi­liz­ing beam orbit is crit­i­cal for ad­vanced syn­chro­tron ra­di­a­tion light sources. The beam orbit can be af­fected by many sources. To main­tain a good orbit sta­bil­ity, global orbit feed­back sys­tems (OFB) has been widely used. How­ever, the BPM ther­mal de­for­ma­tion would lead to BPM mis­read­ing, which can not be han­dled by OFB. Usu­ally, extra di­ag­nos­tics, such as po­si­tion trans­duc­ers, is needed to mea­sure the de­for­ma­tion de­pen­dency of BPM read­ings. Here, an al­ter­na­tive ap­proach by using the ma­chine op­er­a­tion his­toric data, in­clud­ing BPM tem­per­a­ture, in­ser­tion de­vice (ID) gaps and cor­rec­tor cur­rents, is pre­sented. It is demon­strated at Hefei Light Source (HLS). The av­er­age orbit shift due to BPM ther­mal de­for­ma­tion is about 34.5 mi­crons/de­gree Cel­sius (hor­i­zon­tal) and 20.0 mi­crons/de­gree Cel­sius (ver­ti­cal).  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-THPOPT008  
About • Received ※ 19 May 2022 — Revised ※ 14 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 19 June 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPOTK061 Machine Learning Approach to Temporal Pulse Shaping for the Photoinjector Laser at CLARA laser, target, experiment, electron 2917
 
  • A.E. Pollard, D.J. Dunning, W.A. Okell, E.W. Snedden
    STFC/DL/ASTeC, Daresbury, Warrington, Cheshire, United Kingdom
  
  The tem­po­ral pro­file of the elec­tron bunch is of crit­i­cal im­por­tance in ac­cel­er­a­tor areas such as free-elec­tron lasers and novel ac­cel­er­a­tion. In FELs, it strongly in­flu­ences fac­tors in­clud­ing ef­fi­ciency and the pro­file of the pho­ton pulse gen­er­ated for user ex­per­i­ments, while in novel ac­cel­er­a­tion tech­niques it con­tributes to en­hanced in­ter­ac­tion of the wit­ness beam with the dri­ving elec­tric field. Work is in progress at the CLARA fa­cil­ity at Dares­bury Lab­o­ra­tory on tem­po­ral shap­ing of the ul­tra­vi­o­let pho­toin­jec­tor laser, using a fused-sil­ica acousto-op­tic mod­u­la­tor. Gen­er­at­ing a user-de­fined (pro­gram­ma­ble) time-do­main tar­get pro­file re­quires find­ing the cor­re­spond­ing spec­tral phase con­fig­u­ra­tion of the shaper; this is a non-triv­ial prob­lem for com­plex pulse shapes. Phys­i­cally in­formed ma­chine learn­ing mod­els have shown great promise in learn­ing com­plex re­la­tion­ships in phys­i­cal sys­tems, and so we apply ma­chine learn­ing tech­niques here to learn the re­la­tion­ships be­tween the spec­tral phase and the tar­get tem­po­ral in­ten­sity pro­files. Our ma­chine learn­ing model ex­tends the range of avail­able pho­toin­jec­tor laser pulse shapes by al­low­ing users to achieve phys­i­cally re­al­is­able con­fig­u­ra­tions for ar­bi­trary tem­po­ral pulse shapes.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-THPOTK061  
About • Received ※ 30 May 2022 — Revised ※ 15 June 2022 — Accepted ※ 01 July 2022 — Issue date ※ 03 July 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPOMS032 Advances in the Optimization of Medical Accelerators proton, medical-accelerators, FEL, detector 3030
 
  • C.P. Welsch
    Cockcroft Institute, Warrington, Cheshire, United Kingdom
  • C.P. Welsch
    The University of Liverpool, Liverpool, United Kingdom
  
  Funding: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska Curie grant agreement No 675265.
Be­tween 2016 and 2020, 15 Fel­lows have car­ried out col­lab­o­ra­tive re­search within the 4 M€ Op­ti­miza­tion of Med­ical Ac­cel­er­a­tors (OMA) EU-funded in­no­v­a­tive train-ing net­work. Based at uni­ver­si­ties, re­search and clin­i­cal fa­cil­i­ties, as well as in­dus­try part­ners in sev­eral Eu­ro­pean coun­tries, the Fel­lows have suc­cess­fully de­vel­oped a range of beam and pa­tient imag­ing tech­niques, im­proved bi­o­log­i­cal and phys­i­cal mod­els in Monte Carlo codes, and also helped im­prove the de­sign of ex­ist­ing and fu­ture clin­i­cal fa­cil­i­ties. This con­tri­bu­tion pre­sents three se­lected OMA re­search high­lights: the use of Medip­ix3 for dosime­try and real-time beam mon­i­tor­ing, stud­ies into the tech­ni­cal chal­lenges for FLASH pro­ton ther­apy, rec­og­nized by the Eu­ro­pean Jour­nal of Med­ical Physics’ 2021 Galileo Gali-lei Award, and re­search into novel mon­i­tors for in-vivo dosime­try that emerged on the back of the OMA net­work. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-THPOMS032  
About • Received ※ 05 June 2022 — Revised ※ 15 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 02 July 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPOMS048 Challenge Based Innovation "Accelerators for the Environment" FEM, background, HOM 3077
 
  • N. Delerue
    Université Paris-Saclay, CNRS/IN2P3, IJCLab, Orsay, France
  • P. Burrows
    JAI, Oxford, United Kingdom
  • R. Holland, L. Rinolfi
    ESI, Archamps, France
  • E. Métral, M. Vretenar
    CERN, Meyrin, Switzerland
  
  Funding: This project has received funding from the European Union’s Horizon 2020 Research and Innovation programme under Grant Agreement No 101004730.
We pre­sent an ini­tia­tive to fos­ter new ideas about the ap­pli­ca­tions of ac­cel­er­a­tors to the En­vi­ron­ment. Called "Chal­lenge Based In­no­va­tion" this ini­tia­tive will gather four teams each of six mas­ter-level stu­dents each com­ing from dif­fer­ent aca­d­e­mic back­grounds. As part of the EU-funded I.​FAST pro­ject (In­no­va­tion Fos­ter­ing in Ac­cel­er­a­tor Sci­ence and Tech­nol­ogy), they will gather dur­ing 10 days in Ar­champs near CERN to re­ceive high level lec­tures on ac­cel­er­a­tors and the en­vi­ron­ment and to brain­storm on pos­si­ble new ap­pli­ca­tions of ac­cel­er­a­tors for the en­vi­ron­ment. At the end of the gath­er­ing, they will pre­sent their pro­ject at CERN to a jury made of ex­perts. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-THPOMS048  
About • Received ※ 09 June 2022 — Revised ※ 10 June 2022 — Accepted ※ 20 June 2022 — Issue date ※ 01 July 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)