Abstract
This paper presents a comparative study of LLM-guided parameter tuning and Bayesian Optimization (BO) for automated PI parameter adjustment in Low Level Radio Frequency (LLRF) systems. Both methods demonstrate effective performance across continuous wave and pulsed operation modes, addressing the challenges of traditional manual tuning in superconducting accelerator facilities. Multi-cavity validation experiments were conducted on both operation modes. For continuous wave 2-parameter optimization, both methods converge to optimal regions within 15 iterations. For pulsed 6-parameter optimization involving coupled amplitude-phase control loops, both methods achieve satisfactory results in around 20 iterations, meeting stability requirements for beam operation. Comparative analysis reveals distinct application advantages: BO is better suited for large-scale batch optimization scenarios, particularly excelling in multi-cavity parallel commissioning and high-dimensional parameter space exploration due to its systematic probabilistic framework. The LLM-guided approach is more appropriate for online optimization scenarios with strict operational constraints, where its conservative optimization strategy and traceable reasoning process make it ideal for parameter fine-tuning during operations. The study provides practical method selection guidelines for intelligent operation of large-scale accelerator facilities.
Funding Information
  • Intelligent Low-Level Radio Frequency (LLRF) Control Algorithms for Superconducting Radio Frequency (RF) Cavities (E129851YR0)
  • National Natural Science Foundation of China (U22A20261)
  • Applications of Artificial Intelligence in the Stability Study of Superconducting Linear Accelerators (E429851YR0)
  • Large Research Infrastructures China initiative Accelerator Driven System Project (2017-000052-75-01-000590)

This publication has 17 references indexed in Scilit: