| Paper |
Title |
Page |
| MOP036 |
A New Approach for Canadian Light Source Future Orbit Correction System Driven by Neural Network |
102 |
| |
- S. Saadat, M.J. Boland
CLS, Saskatoon, Saskatchewan, Canada
- M.J. Boland
University of Saskatchewan, Saskatoon, Canada
|
|
| |
The Orbit Correction System (OCS) of the CLS comprises 48 sets of BPMs. Each BPM has the ability to measure the position of the beam in both the X-Y directions and can record data at a rate of 900 times per second. The Inverse Response Matrix is utilized to determine the optimal strength of the 48 sets of orbit correctors in both the X-Y directions, in order to ensure that the beam follows its desired path. The Singular Value Decomposition function is replaced by a neural network algorithm to serve as the brain of the orbit correction system in this study. The training model’s design includes three hidden layers, and within each layer, there are 96 nodes. The neural network’s outputs for regular operations in CLS exhibit a Mean Square Error of 10-7. Various difficult scenarios were created to test the OCS at 8.0 mA, using offsets in different sections of the storage ring. However, the new model was able to produce the necessary Orbit Correctors signals without any trouble.
|
|
|
Poster MOP036 [1.438 MB]
|
|
| DOI • |
reference for this paper
※ doi:10.18429/JACoW-IBIC2023-MOP036
|
|
| About • |
Received ※ 14 July 2023 — Revised ※ 09 September 2023 — Accepted ※ 28 September 2023 — Issue date ※ 30 September 2023 |
| Cite • |
reference for this paper using
※ BibTeX,
※ LaTeX,
※ Text/Word,
※ RIS,
※ EndNote (xml)
|
|
| |