| Paper | Title | Page | |||
|---|---|---|---|---|---|
| THOB03 | Adaptive Control and Machine Learning for Particle Accelerator Beam Control and Diagnostics | 466 | |||
|
|||||
|
In this tutorial, we start by reviewing some topics in control theory, including adaptive and model-independent feedback control algorithms that are robust to uncertain and time-varying systems, and provide some examples of their application for particle accelerator beams at both hadron and electron machines. We then discuss recent developments in machine learning (ML) and show some examples of how ML methods are being developed for accelerator controls and diagnostics, such as online surrogate models that act as virtual observers of beam properties. Then we give an overview of adaptive machine learning (AML) in which adaptive model-independent methods are combined with ML-based methods so that they are robust for and applicable to time-varying systems*. Finally, we present some recent applications of AML for accelerator controls and diagnostics. In particular we present recently developed adaptive latent space tuning methods and show how they can be used as virtual adaptive predictors of an accelerator beam’s longitudinal phase space as well as all of the other 2D projections of a beam’s 6D phase space**,***. Throughout the tutorial we will present recent results of various algorithms which have been applied at the LANSCE ion accelerator, the EuXFEL and LCLS FELs, the FACET plasma wakefield accelerator facility, the NDCXII ion accelerator, and the HiRES compact UED.
* A. Scheinker, et al. Physical review letters 121.4 (2018): 044801. ** A. Scheinker, et al. arXiv preprint arXiv:2102.10510 (2021). *** A. Scheinkeret al. arXiv preprint arXiv:2105.03584(2021). |
|||||
|
|
||||
|
Slides THOB03 [24.453 MB] | ||||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IBIC2021-THOB03 | ||||
| About • | paper received ※ 04 September 2021 paper accepted ※ 26 September 2021 issue date ※ 25 October 2021 | ||||
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | ||||