The application of machine learning and nature-inspired optimization methods, like for example genetic algorithms (GA) and particle swarm optimization (PSO) can be found in various scientific/technical areas. In recent years, these approaches are finding application in accelerator physics to a greater extent. In this paper, nature-inspired optimization as well as the machine learning will be shortly introduced and their application to the accelerator facility at GSI/FAIR will be presented. For the heavy-ion synchrotron SIS18 at GSI, the multi-objective GA/PSO optimization resulted in a significant improvement of multi-turn injection performance and subsequent transmission for intense beams. An automated injection optimization with genetic algorithms at the CRYRING@ESR ion storage ring has been performed. The usage of machine learning for a beam diagnostic application, where reconstruction of space-charge distorted beam profiles from ionization profile monitors is performed, will also be shown. First results and the experience gained will be presented.

Keywords:

PACS: 29.20.db, 29.27.Ac

You currently do not have access to the full text article.
Recommend the journal to your library today!

References

1. P. Spiller et al., FAIR Technical Design Report, 2008. Google Scholar
2. E. Mustafin et al., Nucl. Instrum. Methods A 510, 199 (2003). Web of Science, ADS, Google Scholar
3. S. Appel et al., Nucl. Instrum. Methods A 852, 73 (2017). Web of Science, ADS, Google Scholar
4. S. Reimann et al., Building an operation team for FAIR nearly from scratch, presentation at WAO10, 2016. Google Scholar
5. S. Ratschow et al., The high energy beam transport system for FAIR, in Proc. EPAC08 (Genoa, Italy, 2008), pp. 3608–3610. Google Scholar
6. F. Herfurth et al., Commissioning of the low energy storage ring facility CRYRING@ESR, in Proc. 11th Workshop on Beam Cooling and Related Topics (COOL’17) (Bonn, Germany, 2017), pp. 81–83. Google Scholar
7. W. Geithner et al., Hyperfine Interact. 238, 13 (2017). ADS, Google Scholar
8. O. Gorda et al., Phys. Scr. T166, 14043 (2015). Web of Science, Google Scholar
9. A. Källberg and A. Simonsson, Beam steering with image processing in the CRYRING injection beamline, in Proc. DIPAC’99 (Checster, UK, 1999), pp. 118–119. Google Scholar
10. A. Konak, D. W. Coit and A. E. Smith, Reliab. Eng. Syst. Saf. 91, 992 (2006). Web of Science, Google Scholar
11. X. Pang and L. Rybarcyk, Nucl. Instrum. Methods A 741, 124 (2013). Web of Science, ADS, Google Scholar
12. L. Groening et al., Upgrade of the universal linear accelerator UNILAC for FAIR, in Proc. 7th Int. Particle Accelerator Conf. (IPAC’16) (Busan, Korea, 2016), pp. 880–882. Google Scholar
13. F. Fortin and D. Rainville, J. Mach. Learn. Res. 13, 2171 (2012), https://github.com/DEAP/deap. Web of Science, Google Scholar
14. A. Shishlo et al., Procedia Comput. Sci. 51, 1272 (2015). https://doi.org/10.1016/j.procs.2015.05.312, https://github.com/PyORBIT-Collaboration. Google Scholar
15. S. Appel, O. Boine-Frankenheim, Multi-turn injection into a heavy-ion synchrotron in the presence of space charge, arxiv:1403.5972v1. Google Scholar
16. S. Appel et al., Nucl. Instrum. Methods A 866, 36 (2017). Web of Science, ADS, Google Scholar
17. Y. El-Hayek et al., Initial beam loss and control of dynamic vacuum effects in SIS18, in Proc. IPAC’13 (Shanghai, China, 2013), pp. 300–302. Google Scholar
18. C. Kleffner et al., Status of the FAIR Proton Linac, in Proc. LINAC’18 (Beijing, China, 2018), pp. 787–789. Google Scholar
19. F. Wilhelmstötter, Jenetics advanced genetic algorithm, http://jenetics.io. Google Scholar
20. W. Geithner et al., Genetic algorithms for machine optimization in the FAIR control system environment, in Proc. IPAC’18 (Vancouver, Canada, 2018), pp. 4712–4715. Google Scholar
21. A. Géron, Hands-On Machine Learning with Scikit-Learn and TensorFlow (O’Reilly, 2017). Google Scholar
22. R. Singh, M. Sapinski and D. M. Vilsmeier, Simulation supported profile reconstruction with machine learning, in Proc. 6th Int. Beam Instrumentation Conf. (IBIC’17) (Grand Rapids, MI, USA, 2017), pp. 350–354. Google Scholar
23. D. Vilsmeier et al., Reconstructing Space-charge distorted IPM profiles with machine learning algorithms, in Proc. IPAC’18 (Vancouver, BC, Canada, 2018), pp. 2099–2102. Google Scholar
24. S. Levasseur et al., Time-Resolved transverse beam profile measurements with a rest gas ionisation profile monitor based on hybrid pixel detectors, in Proc. IPAC’18 (Vancouver, BC, Canada, 2018), pp. 2361–2364. Google Scholar
25. M. Sapinski et al., Application of machine learning for the IPM-based profile reconstruction, in Proc. HB’18 (Daejeon, Korea, 2018), pp. 410–415. Google Scholar