Author: Viefhaus, J.
Paper Title Page
MOCPL02 Modernization of Experimental Data Taking at BESSY II 65
 
  • R. Müller, A.F. Balzer, P. Baumgärtel, G. Hartmann, O.-P. Sauer, J. Viefhaus
    HZB, Berlin, Germany
 
  The modernization approach for the automation of experimental data taking at BESSY II will be based on the data model of devices. Control of new components and refactoring and reassembly of legacy software should fit into a device based framework. This approach guides the integration of motors, encoders, detectors and auxiliary subsystems. In addition modern software stacks are enabled to provide automation tools for beamline and experimental flow control and DAQ. Strategic goal is the mapping of real beamline components into modelling software to provide the corresponding digital twin. First tests applying DMA methods within this context for tuning are promising.  
slides icon Slides MOCPL02 [15.580 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-MOCPL02  
About • paper received ※ 02 October 2019       paper accepted ※ 09 October 2019       issue date ※ 30 August 2020  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUCPL01 Adding Machine Learning to the Analysis and Optimization Toolsets at the Light Source BESSY II 754
 
  • L. Vera Ramirez, T. Mertens, R. Müller, J. Viefhaus
    HZB, Berlin, Germany
  • G. Hartmann
    University of Kassel, Kassel, Germany
 
  The Helmholtz Association has initiated the implementation of the Data Management and Analysis concept across its centers in Germany. At Helmholtz-Zentrum Berlin, both the beamline and the machine (accelerator) groups have started working towards setting up the infrastructure and tools to introduce modern analysis, optimization, automation and AI techniques for improving the performance of the (large scale) user facility and its experimental setups. This paper focuses on our first steps with Machine Learning techniques over the past months at BESSY II as well as organizational topics and collaborations. The presented results correspond to two complementary scenarios. The first one is based on supervised ML models trained with real accelerator data, whose target are real-time predictions for several measurements (lifetime, efficiency, beam loss, …); some of these techniques are also used for additional tasks such as outlier detection or feature importance analysis. The second scenario includes first prototypes towards self-tuning of machine parameters in different optimization cases (injection efficiency, orbit correction, …) with Deep Reinforcement Learning agents.  
slides icon Slides TUCPL01 [8.894 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-TUCPL01  
About • paper received ※ 27 September 2019       paper accepted ※ 10 October 2019       issue date ※ 30 August 2020  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)