Accelerator beam orbit prediction based on multi-stage cascaded BP neural networks

Cao Zigeng; Yan Chunman; Yang Xuhui; Guo Yuhui

doi:10.11884/HPLPB202335.230109

Volume 35 Issue 12

Nov. 2023

Turn off MathJax

Article Contents

Article Navigation > High Power Laser and Particle Beams > 2023 > 35(12): 124002

Cao Zigeng, Yan Chunman, Yang Xuhui, et al. Accelerator beam orbit prediction based on multi-stage cascaded BP neural networks[J]. High Power Laser and Particle Beams, 2023, 35: 124002. doi: 10.11884/HPLPB202335.230109

Citation:

Cao Zigeng, Yan Chunman, Yang Xuhui, et al. Accelerator beam orbit prediction based on multi-stage cascaded BP neural networks[J]. High Power Laser and Particle Beams, 2023, 35: 124002. doi: 10.11884/HPLPB202335.230109

Citation:

PDF( 3111 KB)

Accelerator beam orbit prediction based on multi-stage cascaded BP neural networks

doi: 10.11884/HPLPB202335.230109

Cao Zigeng^{1, 2
,},
Yan Chunman¹,
Yang Xuhui²,
Guo Yuhui^{2
,
,}

1.
College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou 730070, China
2.
Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou 730000, China

Received Date: 2023-04-28
Accepted Date: 2023-08-29
Rev Recd Date: 2023-08-17

Available Online: 2023-11-04

Publish Date: 2023-12-15

Abstract

Abstract

Since accelerator beam orbit correction is crucial for stable operation of accelerators, accurate prediction of the changes of the accelerator beam orbit is also essential for automated beam calibration. Precise predictions of beam orbit changes can provide reliable information for adjusting accelerator control parameters to achieve precise control and regulation of beam orbit. In this paper, based on a multi-stage cascaded back propagation (BP) neural network and simulated accelerator data, the beam transport process in the medium energy transfer section of a linear accelerator is studied and an accelerator beam orbit prediction model is constructed to predict beam orbit parameters. The results show that the proposed multi-stage cascaded BP neural network achieves higher prediction accuracy and reliability than the prediction model built using a traditional single hidden layer BP neural network. This provides an effective method for optimally designing the medium energy transfer section of the linear accelerator and automating the calibration of the beam orbit.
- accelerator driven sub-critical system,
- medium energy beam transport,
- cascade network,
- back propagation neural network,
- beam orbit prediction

FullText(HTML)

References(19)

References

[1]	肖国青, 徐瑚珊, 王思成. HIAF及CiADS项目进展与展望[J]. 原子核物理评论, 2017, 34(3):275-283 Xiao Guoqing, Xu Hushan, Wang Sicheng. HIAF and CiADS national research facilities: progress and prospect[J]. Nuclear Physics Review, 2017, 34(3): 275-283
[2]	骆鹏, 王思成, 胡正国, 等. 加速器驱动次临界系统——先进核燃料循环的选择[J]. 物理, 2016, 45(9):569-577 Luo Peng, Wang Sicheng, Hu Zhengguo, et al. Accelerator driven sub-critical systems——a promising solution for cycling nuclear fuel[J]. Physics, 2016, 45(9): 569-577
[3]	汪柏帆, 袁辰彰, 蔡汉杰, 等. CAFe DUMP前刮束器的设计研制[J]. 原子核物理评论, 2022, 39(3):326-333 Wang Baifan, Yuan Chenzhang, Cai Hanjie, et al. Design and development of the collimator in front of the CAFe DUMP[J]. Nuclear Physics Review, 2022, 39(3): 326-333
[4]	陈伟龙. 基于束流损失控制的LEBT设计[D]. 兰州: 中国科学院研究生院(近代物理研究所), 2016: 53-55 Chen Weilong. LEBT design based on beam loss control[D]. Lanzhou: Institute of Modern Physics, Chinese Academy of Sciences, 2016: 53-55
[5]	万金宇, 孙正, 张相, 等. 机器学习在大型粒子加速器中的应用回顾与展望[J]. 强激光与粒子束, 2021, 33:094001 doi: 10.11884/HPLPB202133.210199 Wan Jinyu, Sun Zheng, Zhang Xiang, et al. Machine learning applications in large particle accelerator facilities: review and prospects[J]. High Power Laser and Particle Beams, 2021, 33: 094001 doi: 10.11884/HPLPB202133.210199
[6]	Yang Xuhui, Zhou Qingguo, Wang Jinqiang, et al. Predictive control modeling of ADS’s MEBT using BPNN to reduce the impact of noise on the control system[J]. Annals of Nuclear Energy, 2019, 132: 576-583. doi: 10.1016/j.anucene.2019.06.034
[7]	Bozoki E, Friedman A. Neural networks and orbit control in accelerators[R]. Washington: Brookhaven National Lab. , 1994.
[8]	Meier E, Morgan M J, Biedron S, et al. Electron beam energy stabilization using a neural network hybrid controller at the Australian Synchrotron Linac[C]//Particle Accelerator Conference. 2009: 1201-1203.
[9]	李超, 张智磊, 齐新, 等. TOPOPIC对强流束流在周期FODO结构中的传输研究[J]. 原子核物理评论, 2015, 32(2):191-195 Li Chao, Zhang Zhilei, Qi Xin, et al. High intensity beam transport study with TOPOPIC in FODO structure[J]. Nuclear Physics Review, 2015, 32(2): 191-195
[10]	Sosa A G, Baron R, Danared H, et al. Status of testing and commissioning of the medium energy beam transport line of the ESS normal conducting LINAC[C]//Proceedings of the 31st Linear Accelerator Conference. 2022: 376-379.
[11]	周浩. 加速器束流诊断中数字BPM系统研究[D]. 合肥: 中国科学技术大学, 2009: 1-2 Zhou Hao. Research on DBPM system in accelerator beam diagnosis[D]. Hefei: University of Science and Technology of China, 2009: 1-2
[12]	袁任贤, 叶恺容. 束流位置探头的理论设计[J]. 核技术, 2003, 26(4):261-265 Yuan Renxian, Ye Kairong. Design of beam position monitor[J]. Nuclear Techniques, 2003, 26(4): 261-265
[13]	Chen Xiaolong, Jia Yongzhi, Qi Xin, et al. Orbit correction based on improved reinforcement learning algorithm[J]. Physical Review Accelerators and Beams, 2023, 26: 044601. doi: 10.1103/PhysRevAccelBeams.26.044601
[14]	魏源源, 秦庆. 响应矩阵分析方法在BEPC储存环上的应用[J]. 高能物理与核物理, 2006, 30(s1):43-45 Wei Yuanyuan, Qin Qing. Application of response matrix at the BEPC storage ring[J]. High Energy Physics and Nuclear Physics, 2006, 30(s1): 43-45
[15]	李京纬, 刘祖平, 王筠华. 合肥光源电子储存环束流闭轨的局部校正[J]. 强激光与粒子束, 1998, 10(2):291-295 Li Jingwei, Liu Zuping, Wang Yunhua. Local correction of electron beam closed orbit in HLS storage ring[J]. High Power Laser and Particle Beams, 1998, 10(2): 291-295
[16]	张峡, 黄团华, 赵晓岩. 基于遗传算法进行加速器自动调束[J]. 强激光与粒子束, 2004, 16(9):1222-1224 Zhang Xia, Huang Tuanhua, Zhao Xiaoyan. Automatic beam tuning in accelerator based on genetic algorithms[J]. High Power Laser and Particle Beams, 2004, 16(9): 1222-1224
[17]	Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536. doi: 10.1038/323533a0
[18]	鲁智勇, 张权, 张希, 等. 等效分组级联BP网络模型及其应用[J]. 电子学报, 2010, 38(6):1349-1354 Lu Zhiyong, Zhang Quan, Zhang Xi, et al. Equivalent grouping-cascaded BP network model and its applications[J]. Acta Electronica Sinica, 2010, 38(6): 1349-1354
[19]	Heaton J. Introduction to neural networks with Java[M]. 2nd ed. St Louis: Heaton Research, 2008: 159.