Paper |
Title |
Page |
TUPOPT058 |
A Machine Learning Approach to Electron Orbit Control at the 1.5 GeV Synchrotron Light Source DELTA |
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)
|
|
|
TUPOPT059 |
Machine Learning Methods for Chromaticity Control at the 1.5 GeV Synchrotron Light Source DELTA |
1141 |
|
- D. Schirmer, A. Althaus, T. Schüngel
DELTA, Dortmund, Germany
|
|
|
In the past, the chromaticity values at the DELTA electron storage ring were manually adjusted using 15 individual sextupole power supply circuits, which are combined into 7 magnet families. To automate and optimize the time-consuming setting process, various machine learning (ML) approaches were investigated. For this purpose, simulations were first performed using a storage ring model and the performance of different neural network (NN) based models was compared. Subsequently, the neural networks were trained with experimental data and successfully implemented for chromaticity correction in real accelerator operation.
|
|
DOI • |
reference for this paper
※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOPT059
|
|
About • |
Received ※ 20 May 2022 — Revised ※ 11 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 21 June 2022 |
Cite • |
reference for this paper using
※ BibTeX,
※ LaTeX,
※ Text/Word,
※ RIS,
※ EndNote (xml)
|
|
|