Paper | Title | Page |
---|---|---|
THAL01 | Machine Learning Tools Improve BESSY II Operation | 784 |
|
||
At the HZB user facility BESSY II Machine Learning (ML) technologies aim at advanced analysis, automation, explainability and performance improvements for accelerator and beamline operation. The development of these tools is intertwined with improvements of the prediction part of the digital twin instances at BESSY II [*] and the integration into the Bluesky Suite [**,***]. On the accelerator side, several use cases have recently been identified, pipelines designed and models tested. Previous studies applied Deep Reinforcement Learning (RL) to booster current and injection efficiency. RL now tackles a more demanding scenario: the mitigation of harmonic orbit perturbations induced by external civil noise sources. This paper presents methodology, design and simulation phases as well as challenges and first results. Further ML use cases under study are, among others, anomaly detection prototypes with anomaly scores for individual features.
[*] P. Schnizer et. al, IPAC21 [**] D. Allan, T. Caswell, S. Campbell and M. Rakitin, Synchrot. Radiat. News 32 19-22, 2019 [***] W. Smith et. al, this conference |
||
Slides THAL01 [9.849 MB] | ||
DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2021-THAL01 | |
About • | Received ※ 08 October 2021 Revised ※ 24 October 2021 Accepted ※ 21 November 2021 Issue date ※ 29 January 2022 | |
Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
FRBR03 | Status of Bluesky Deployment at BESSY II | 1064 |
|
||
The modernization plan for the experimental DAQ at the BESSY II is underpinned by the capabilities provided by the Bluesky software ecosystem. To interface with the hardware Bluesky relies on the Ophyd library, that provides a consistent high-level interface across a wide-range of devices. Many elements of the accelerator, some beamlines and endstations are adopting the Bluesky software. To meet FAIR data obligations, the capture of metadata with Bluesky and the export into a permanent and easily accessible storage called ICAT are investigated. Finally, initial studies to investigate the integration of ML methods, like reinforcement learning were performed. This paper reports on the work that has been done so far at BESSY II to adopt Bluesky, problems that have been overcome and lessons learned. | ||
Slides FRBR03 [2.338 MB] | ||
DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2021-FRBR03 | |
About • | Received ※ 08 October 2021 Revised ※ 20 October 2021 Accepted ※ 22 December 2021 Issue date ※ 25 February 2022 | |
Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |