000358352 001__ 358352
000358352 005__ 20250310164730.0
000358352 0247_ $$2doi$$a10.18429/JACOW-IPAC2024-TUPS59
000358352 0247_ $$2datacite_doi$$a10.15120/GSI-2025-00536
000358352 037__ $$aGSI-2025-00536
000358352 041__ $$aEnglish
000358352 1001_ $$0P:(DE-Ds200)OR0031$$aAppel, Sabrina$$b0$$eCorresponding author$$ugsi
000358352 1112_ $$a15th International Particle Accelerator Conference$$cNashville, Tennessee$$d2024-05-19 - 2024-05-24$$gIPAC2024$$wUSA
000358352 245__ $$aData-driven model predictive control for automated optimization of injection into the SIS18 synchrotron
000358352 260__ $$aGeneva, Switzerland$$bJACoW Publishing$$c2024
000358352 300__ $$a1800 - 1803
000358352 3367_ $$2ORCID$$aCONFERENCE_PAPER
000358352 3367_ $$033$$2EndNote$$aConference Paper
000358352 3367_ $$2BibTeX$$aINPROCEEDINGS
000358352 3367_ $$2DRIVER$$aconferenceObject
000358352 3367_ $$2DataCite$$aOutput Types/Conference Paper
000358352 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1741075262_1280620
000358352 500__ $$aPublished by JACoW Publishing under the terms of the Creative Commons Attribution 4.0 license.
000358352 520__ $$aIn accelerator labs like GSI/FAIR, automating complex systems is key for maximizing physics experiment time. This study explores the application of a data-driven model predictive control (MPC) to refine the multi-turn injection (MTI) process into the SIS18 synchrotron, departing from conventional numerical optimization methods. MPC is distinguished by its reduced number of optimization steps and superior ability to control performance criteria, effectively addressing issues like delayed outcomes and safety concerns, including septum protection. The study focuses on a highly sample-efficient MPC approach based on Gaussian processes, which lies at the intersection of model-based reinforcement learning and control theory. This approach merges the strengths of both fields, offering a unified and optimized solution and yielding a safe and fast state-based optimization approach beyond classical reinforcement learning and Bayesian optimization. Our study lays the groundwork for enabling safe online training for the SS18 MTI issue, showing great potential for applying data-driven control in similar scenarios.
000358352 536__ $$0G:(DE-HGF)POF4-899$$a899 - ohne Topic (POF4-899)$$cPOF4-899$$fPOF IV$$x0
000358352 588__ $$aDataset connected to DataCite
000358352 650_7 $$2Other$$aAccelerator Physics
000358352 650_7 $$2Other$$amc6-beam-instrumentation-controls-feedback-and-operational-aspects - MC6: Beam Instrumentation, Controls, Feedback, and Operational Aspects
000358352 650_7 $$2Other$$aMC6.D13 - MC6.D13 Machine Learning
000358352 693__ $$0EXP:(DE-Ds200)no_experiment-20200803$$1EXP:(DE-Ds200)theory-20200803$$5EXP:(DE-Ds200)no_experiment-20200803$$atheory$$eno experiment theory work (theory)$$x0
000358352 7001_ $$0P:(DE-HGF)0$$aHirlaender, Simon$$b1
000358352 7001_ $$0P:(DE-Ds200)OR12417$$aMadysa, Nico$$b2$$ugsi
000358352 7001_ $$0P:(DE-HGF)0$$aPilat, Fulvia$$b3$$eEditor
000358352 7001_ $$0P:(DE-HGF)0$$aFischer, Wolfram$$b4$$eEditor
000358352 7001_ $$0P:(DE-HGF)0$$aSaethre, Robert$$b5$$eEditor
000358352 7001_ $$0P:(DE-HGF)0$$aAnisimov, Petr$$b6$$eEditor
000358352 7001_ $$0P:(DE-HGF)0$$aAndrian, Ivan$$b7$$eEditor
000358352 773__ $$a10.18429/JACOW-IPAC2024-TUPS59
000358352 8564_ $$uhttps://repository.gsi.de/record/358352/files/TUPS59.pdf$$yOpenAccess
000358352 8564_ $$uhttps://repository.gsi.de/record/358352/files/TUPS59.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000358352 909CO $$ooai:repository.gsi.de:358352$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000358352 9101_ $$0I:(DE-Ds200)20121206GSI$$6P:(DE-Ds200)OR0031$$aGSI Helmholtzzentrum für Schwerionenforschung GmbH$$b0$$kGSI
000358352 9101_ $$0I:(DE-Ds200)20121206GSI$$6P:(DE-Ds200)OR12417$$aGSI Helmholtzzentrum für Schwerionenforschung GmbH$$b2$$kGSI
000358352 9131_ $$0G:(DE-HGF)POF4-899$$1G:(DE-HGF)POF4-890$$2G:(DE-HGF)POF4-800$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0
000358352 9141_ $$y2025
000358352 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000358352 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000358352 920__ $$lno
000358352 9201_ $$0I:(DE-Ds200)APH-20060809OR090$$kAPH$$lAccelerator Physics$$x0
000358352 980__ $$acontrib
000358352 980__ $$aVDB
000358352 980__ $$aUNRESTRICTED
000358352 980__ $$aI:(DE-Ds200)APH-20060809OR090
000358352 9801_ $$aFullTexts