Application of machine learning in BEPCII superconduction radio-frequency cavity fault analysis

Zeng Tongke; Dai Jianping

doi:10.11884/HPLPB202537.240270

Article Contents

Article Navigation > High Power Laser and Particle Beams > 2025 > Corrected proofs

Zeng Tongke, Dai Jianping. Application of machine learning in BEPCII superconduction radio-frequency cavity fault analysis[J]. High Power Laser and Particle Beams. doi: 10.11884/HPLPB202537.240270

Citation:

Zeng Tongke, Dai Jianping. Application of machine learning in BEPCII superconduction radio-frequency cavity fault analysis[J]. High Power Laser and Particle Beams. doi: 10.11884/HPLPB202537.240270

Zeng Tongke, Dai Jianping. Application of machine learning in BEPCII superconduction radio-frequency cavity fault analysis[J]. High Power Laser and Particle Beams. doi: 10.11884/HPLPB202537.240270

Citation:

Zeng Tongke, Dai Jianping. Application of machine learning in BEPCII superconduction radio-frequency cavity fault analysis[J]. High Power Laser and Particle Beams. doi: 10.11884/HPLPB202537.240270

PDF( 2683 KB)

Application of machine learning in BEPCII superconduction radio-frequency cavity fault analysis

doi: 10.11884/HPLPB202537.240270

Zeng Tongke^{1, 2
,},
Dai Jianping^{1
,
,}

1.
Institute of High Energy Physics, Chinese Academy of sciences, Beijing 100049, China
2.
University of Chinese Academy of Sciences, Beijing 100049, China

Received Date: 2024-08-20
Accepted Date: 2025-05-14
Rev Recd Date: 2025-05-13

Available Online: 2025-05-24

Abstract

Abstract

Traditional methods for analyzing superconduction radio-frequency (SRF) cavity faults rely on a priori knowledge, featuring high labor and time costs, poor accuracy and low consistency. They are less efficient when dealing with complex devices and large amounts of data. In this paper, a method for classifying SRF cavity faults based on machine learning algorithms is investigated. Using the SRF cavity fault data generated during the operation of BEPCII, the classification of SRF cavity faults is achieved through image information extraction, feature selection and optimization, machine learning algorithm training, and analyzing the accuracy and consistency of the model via K-fold cross validation. The results of the study show that Random Forest, Support Vector Machine and Bagging algorithms have better classification results when dealing with faulty pictures. The accuracy and consistency of supervised learning methods are significantly higher than those of unsupervised learning. The fault classification realized in this research achieves high accuracy and consistency. It enables to quickly and efficiently distinguish the faults occurring on the SRF cavity of BEPCII. It also provides a reference for the diagnosis of SRF cavity faults in other particle accelerators.
- superconduction radio-frequency cavity faults,
- diagnostic methods,
- image recognition,
- machine learning,
- faults classification

FullText(HTML)

References(16)

References

[1]	王光伟, 沙鹏, 潘卫民, 等. BEPCII高频系统的建造[J]. 中国物理C, 2008(s1):169-171 Wang Guangwei, Sha Peng, Pan Weimin, et al. Construction of the BEPCII RF system[J]. Chinese Physics C, 2008(s1): 169-171
[2]	Solopova A, Carpenter A, Powers T, et al. SRF cavity fault classification using machine learning at CEBAF[R]. Newport News: Thomas Jefferson National Accelerator Facility (TJNAF), 2019.
[3]	Tennant C, Carpenter A, Powers T, et al. Superconducting radio-frequency cavity fault classification using machine learning at Jefferson Laboratory[J]. Physical Review Accelerators and Beams, 2020, 23: 114601. doi: 10.1103/PhysRevAccelBeams.23.114601
[4]	Vidyaratne L, Carpenter A, Powers T, et al. Deep learning based superconducting radio-frequency cavity fault classification at Jefferson laboratory[J]. Frontiers in Artificial Intelligence, 2022, 4: 718950. doi: 10.3389/frai.2021.718950
[5]	Rahman M M, Iftekharuddin K, Carptenter A, et al. Real-time cavity fault prediction in CEBAF using deep learning[C]//Proceedings of the North American Particle Accelerator Conference. 2022: 687-690.
[6]	肖麟阁, 戴建枰, 王群要, 等. BEPCII超导腔失效分析[J]. 强激光与粒子束, 2019, 31:085105 doi: 10.11884/HPLPB201931.190078 Xiao Linge, Dai Jianping, Wang Qunyao, et al. Analysis of the failure of BEPCII SRF cavities[J]. High Power Laser and Particle Beams, 2019, 31: 085105 doi: 10.11884/HPLPB201931.190078
[7]	韩晓微. 彩色图像处理关键技术研究[D]. 沈阳: 东北大学, 2005 Han Xiaowei. Study on key technologies of color image processing[D]. Shenyang: Northeastern University, 2005
[8]	戴聪聪, 罗小燕, 邵凡, 等. 基于CEEMDAN和AR模型的岩体声发射信号特征提取方法研究[J]. 化工矿物与加工, 2018, 47(6):20-24 Dai Congcong, Luo Xiaoyan, Shao Fan, et al. Study on extraction method of rock acoustic emission signals based on CEEMDAN and AR model[J]. Industrial Minerals & Processing, 2018, 47(6): 20-24
[9]	Das K, Behera R N. A survey on machine learning: concept, algorithms and applications[J]. International Journal of Innovative Research in Computer and Communication Engineering, 2017, 5(2): 1301-1309.
[10]	李小斌, 李世银. AdBagging: 自适应抽样参数在线装袋算法[J]. 计算机工程与设计, 2011, 32(12):4095-4099 Li Xiaobin, Li Shiyin. AdBagging: adaptive sampling parameters online bagging algorithm[J]. Computer Engineering and Design, 2011, 32(12): 4095-4099
[11]	孔英会, 车辚辚, 苑津莎, 等. 基于小波分解和数据挖掘中决策树算法的电能质量扰动识别方法[J]. 电网技术, 2007, 31(23):78-82 Kong Yinghui, Che Linlin, Yuan Jinsha, et al. A power quality disturbance identification method based on wavelet decomposition and decision tree algorithm in data mining[J]. Power System Technology, 2007, 31(23): 78-82
[12]	孙吉贵, 刘杰, 赵连宇. 聚类算法研究[J]. 软件学报, 2008, 19(1):48-61 Sun Jigui, Liu Jie, Zhao Lianyu. Clustering algorithms research[J]. High Power Laser and Particle Beams, 2008, 19(1): 48-61
[13]	张宁, 贾自艳, 史忠植. 使用KNN算法的文本分类[J]. 计算机工程, 2005, 31(8):171-172,185 Zhang Ning, Jia Ziyan, Shi Zhongzhi. Text categorization with KNN algorithm[J]. Computer Engineering, 2005, 31(8): 171-172,185
[14]	James G, Witten D, Hastie T, et al. An introduction to statistical learning[M]. New York: Springer, 2013: 180-182.
[15]	Foody G M. Status of land cover classification accuracy assessment[J]. Remote Sensing of Environment, 2002, 80(1): 185-201. doi: 10.1016/S0034-4257(01)00295-4
[16]	Veropoulos K, Campbell I C G, Cristianini N. Controlling the sensitivity of support vector machines[C]//Proceedings of the International Joint Conference on AI. 1999: 55-60.