摘要
中国散裂中子源(China Spallation Neutron Source,CSNS)作为一个用户装置,其稳定运行对科学研究的顺利开展具有重要意义。然而,由于加速器系统的高度复杂性,传统的基于阈值的报警机制在应对复杂和多样化的异常时表现出明显的局限性,部分未能及时检测的异常可能引发束流联锁,降低运行效率和稳定性。为了解决这一问题,本文提出了一种基于机器学习的异常检测方法,并开发了CSNS加速器智能值班员样机系统。该系统通过特征工程和无监督学习算法,能够实时监测运行数据并精准识别复杂异常,尤其是对传统方法难以检测的波动形态异常表现出显著优势。样机系统已成功应用于CSNS加速器运行环境,能够准确捕获运行过程中的异常情况并报警,从而提升异常监测的准确性和故障排除效率。
[Background]In accelerator operations,ensuring stable performance is critical for supporting scientific research,particularly for complex systems such as the China Spallation Neutron Source(CSNS).Traditional threshold-based alarm mechanisms often struggle to detect certain intricate anomalies,especially those with complex or transient patterns,leading to gaps in monitoring and increased challenges for operators during fault diagnosis.These undetected anomalies can significantly lower operational efficiency and delay fault resolution.[Purpose]This study aims to develop an intelligent monitoring system for CSNS accelerators to detect complex anomalies and enhance fault detection reliability.[Methods]A machine learning-based framework was proposed to improve anomaly detection in accelerator operations.The method employed unsupervised algorithms to analyze operational data,with a focus on jitter-type anomalies that are challenging for traditional alarms to capture.Cooling water temperature variables were selected as the research objects.The workflow involved data preprocessing,feature extraction,and the application of unsupervised learning models to detect deviations from normal operational patterns.To validate the method,a prototype system for intelligent accelerator monitoring was developed,incorporating realtime data analysis and anomaly detection capabilities.[Results]The proposed method successfully detected jittertype anomalies in various operational datasets,such as cooling water temperatures and power supply parameters,demonstrating its generalizability across different subsystems.Additionally,the prototype system was deployed and validated in the CSNS operational environment,where it effectively identified anomalies.[Conclusions]This machine learning-based anomaly detection approach improves the accuracy and reliability of monitoring in accelerator operations.By addressing the limitations of traditional methods,it provides a more effective and scalable solution for real-time anomaly detection.The prototype system demonstrates the feasibility of implementing intelligent monitoring for complex accelerator systems,contributing to the stability and efficiency of their operation.
作者
彭娜
张玉亮
程司农
何泳成
梅昊
王林
薛康佳
李明涛
吴煊
朱鹏
黄蔚玲
PENG Na;ZHANG Yuliang;CHENG Sinong;HE Yongcheng;MEI Hao;WANG Lin;XUE Kangjia;LI Mingtao;WU Xuan;ZHU Peng;HUANG Weiling(Institute of High Energy Physics,Chinese Academy of Sciences,Beijing 100049,China;University of Chinese Academy of Sciences,Beijing 100049,China;Spallation Neutron Source Science Center,Dongguan 523803,China)
出处
《核技术》
北大核心
2025年第5期11-21,共11页
Nuclear Techniques
基金
国家自然科学基金面上项目(No.12275294)资助。
关键词
机器学习
异常检测
无监督学习
聚类算法
粒子加速器
Machine learning
Anomaly detection
Unsupervised learning
Cluster algorithm
Particle accelerator
