Linear Optics Calibration in a Storage Ring Based on Machine Learning
Source abstract
Abstract
Inevitably, various errors occur in an actual storage ring, such as magnetic field errors, magnet misalignments, and ground settlement deformation, which cause closed orbit distortion and tuning shift. Therefore, linear optics calibration is an essential procedure for storage rings. In this paper, we introduce a new method using machine learning to calibrate linear optics. This method is different from the traditional linear optics from closed orbit (LOCO) method, which is based on singular value decomposition (SVD). The machine learning model does not need to be computed by SVD. Our study shows that the machine-learning-based method can significantly reduce the difference between the model response matrix and the measurement response matrix by adjusting the strength of the quadrupoles.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Optical Systems and Laser Technology · Astronomical Observations and Instrumentation · Optical measurement and interference techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shanghai Synchrotron Radiation Facility, Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China
Shanghai Institute of Applied Physics, Chinese Academy of Sciences, Shanghai 201800, China
School of Physical Science and Technology, ShanghaiTech University, Shanghai 201210, China
Laboratory for Ultrafast Transient Facility, Chongqing University, Chongqing 401331, China
University of Chinese Academy of Sciences, Beijing 100049, China
Funding
National Natural Science Foundation of China · Youth Innovation Promotion Association of CAS
References (39)
Show source-provided references
1. X-ray biomedical imaging beamline at SSRF10.1088/1748-0221/8/08/C08003 ↗
2. Tsakanov, V. (2022). Biomarkers of Radiation in the Environment: Robust Tools for Risk Assessment, Springer.
3. Multi-bunch injection for SSRF storage ring
4. Zhang, Q.L., Jiang, B.C., Tian, S.Q., Zhou, Q.G., and Zhao, Z.T. (2015, January 3–8). Study on beam dynamics of a Knot-APPLE undulator proposed for SSRF. Proceedings of the IPAC15, Richmond, VA, USA.
5. Study of Touschek lifetime in SSRF storage ring
6. Demonstration of Machine Learning-Based Model-Independent Stabilization of Source Properties in Synchrotron Light Sources10.1103/PhysRevLett.123.194801 ↗
7. Investigation of fast ion instability in SSRF10.1016/j.nima.2010.01.008 ↗
8. Vibration control research for the 3rd generation synchrotron light source storage ring mechanical components
9. Zhao, Z.T., Xu, H.J., and Ding, H. (2009, January 4–8). Commissioning of the Shanghai Light Source. Proceedings of the PAC09, Vancouver, BC, Canada.
10. Zhao, Z.T., and Xu, H.J. (2010, January 23–28). Operational Status of the Shanghai Synchrotron Radiation Facility. Proceedings of the IPAC10, Kyoto, Japan.
11. Zhao, Z.T., Yin, L.X., Leng, Y.B., Jiang, B.C., and Tian, S.Q. (2015, January 3–8). Consideration on the future major upgrades of the SSRF storage ring. Proceedings of the IPAC15, Richmond, VA, USA.
12. Betatron coupling measurement and optimization in Indus-2 storage ring10.1063/5.0040000 ↗
13. Linear optics correction based on LOCO at SSRF storage ring
14. Machine learning applications in large particle accelerator facilities: Review and prospects
15. Kaiser, J., Stein, O., and Eichler, A. (2022, January 27–29). Learning-based optimisation of particle accelerators under partial observability without real-world training. Proceedings of the International Conference on Machine Learning, Xiamen, China.
16. Wang, F.Y., Song, M., Edelen, A., and Huang, X. (2019). Machine learning for design optimization of storage ring nonlinear dynamics. arXiv.
17. Demonstration of machine learning-enhanced multi-objective optimization of ultrahigh-brightness lattices for 4th-generation synchrotron light sources10.1016/j.nima.2023.168192 ↗
18. Physics-based deep neural networks for beam dynamics in charged particle accelerators10.1103/PhysRevAccelBeams.23.074601 ↗
19. Machine learning enabled fast evaluation of dynamic aperture for storage ring accelerators10.1088/1367-2630/ac77ac ↗
20. Experimental determination of storage ring optics using orbit response measurements10.1016/S0168-9002(97)00309-4 ↗
21. Safranek, J. (2002, January 3–7). Matlab-based LOCO. Proceedings of the EPAC02, Paris, France.10.2172/800082 ↗
22. Review of linear optics measurement and correction for charged particle accelerators10.1103/PhysRevAccelBeams.20.054801 ↗
23. Linear optics calibration and nonlinear optimization during the commissioning of the SSRF storage ring10.1088/1674-1137/33/S2/021 ↗
24. Deep learning10.1038/nature14539 ↗
25. A logical calculus of the ideas immanent in nervous activity10.1007/BF02478259 ↗
26. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
27. Phoneme recognition using time-delay neural networks10.1109/29.21701 ↗
28. Backpropagation applied to handwritten zip code recognition10.1162/neco.1989.1.4.541 ↗
29. Recent advances in convolutional neural networks10.1016/j.patcog.2017.10.013 ↗
30. A comprehensive survey on graph neural networks10.1109/TNNLS.2020.2978386 ↗
31. Improved breast cancer classification through combining graph convolutional network and convolutional neural network10.1016/j.ipm.2020.102439 ↗
32. Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv.
33. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2–4). Tensorflow: A system for large-scale machine learning. Proceedings of the OSDI16, Savannah, GA, USA.
34. Kim, S., Wimmer, H., and Kim, J. (2022, January 22–25). Analysis of Deep Learning Libraries: Keras, PyTorch, and MXnet. Proceedings of the 2022 IEEE/ACIS 20th International Conference on Software Engineering Research, Management and Applications (SERA), Las Vegas, NV, USA.10.1109/SERA54885.2022.9806734 ↗
35. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
36. Reddi, S.J., Kale, S., and Kumar, S. (2019). On the convergence of adam and beyond. arXiv.
37. Nair, V., and Hinton, G.E. (2010, January 21–24). Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair. Proceedings of the ICML10, Haifa, Israel.
38. Deep Sparse Rectifier Neural Networks
39. Terebilo, A. (2001, January 18–22). Accelerator modeling with MATLAB accelerator toolbox. Proceedings of the PAC01, Chicago, IL, USA.10.2172/800064 ↗