An experimental application of machine learning algorithms to optimize the FEL lasing via beam trajectory tuning at Dalian Coherent Light Source

Sun，Jitao1,3; Li，Xinmeng1,3; Yang，Jiayue1; Zeng，Li2; Shao，Jiahang2,4; Yu，Yong2,4; Zhang，Weiqing1; Yang，Xueming1,4

2024-06-01

10.1016/j.nima.2024.169320

Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment   影响因子和分区

0168-9002

The lasing optimization of Free-Electron Laser (FEL) facilities is a time-consuming and challenging task. Instead of operating manually by experienced operators, implementation of machine learning algorithms offers a rapid and adaptable approach for FEL lasing optimization. Recently, such an experiment has been conducted at the vacuum ultraviolet FEL facility - Dalian Coherent Light Source (DCLS). Four algorithms, namely the standard and the neural network-based genetic algorithms, the deep deterministic policy gradient and the soft actor critic reinforcement learning algorithms, have been employed to enhance the FEL intensity by optimizing the electron beam trajectory. These algorithms have shown notable efficacy in enhancing the FEL lasing, especially the reinforcement learning ones which achieved convergence within only approximately 400 iterations. This study demonstrates the validity of machine learning algorithms for FEL lasing optimization, providing a forward-looking perspective on the automatic operation of DCLS.

Dalian Coherent Light Source Deep reinforcement learning FEL lasing optimization Free-electron laser Genetic algorithm

SCI ; EI

英语

通讯

PHYSICS

2-s2.0-85189854815

Scopus

1.Dalian Coherent Light Source and State Key Laboratory of Molecular Reaction Dynamics,Dalian Institute of Chemical Physics,Chinese Academy of Sciences,Dalian,116023,China
2.Institute of Advanced Science Facilities,Shenzhen,518107,China
3.University of Chinese Academy of Sciences,Beijing,100049,China
4.Center for Advanced Light Source,College of Science,Southern University of Science and Technology,Shenzhen,518055,China

Sun，Jitao,Li，Xinmeng,Yang，Jiayue,et al. An experimental application of machine learning algorithms to optimize the FEL lasing via beam trajectory tuning at Dalian Coherent Light Source[J]. Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment,2024,1063.

Sun，Jitao.,Li，Xinmeng.,Yang，Jiayue.,Zeng，Li.,Shao，Jiahang.,...&Yang，Xueming.(2024).An experimental application of machine learning algorithms to optimize the FEL lasing via beam trajectory tuning at Dalian Coherent Light Source.Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment,1063.

Sun，Jitao,et al."An experimental application of machine learning algorithms to optimize the FEL lasing via beam trajectory tuning at Dalian Coherent Light Source".Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 1063(2024).