1.7 MV串列加速器调束优化研究  

1.7 MV Tandem Accelerator Beam Tuning Optimization

作　　者：蒋冉 李爱玲[1] 崔保群[1] 唐兵[1] 陈浩南 王云峰 JIANG Ran;LI Ailing;CUI Baoqun;TANG Bing;CHEN Haonan;WANG Yunfeng(Department of Nuclear Physics,China Institute of Atomic Energy,Beijing 102413,China)

机构地区：[1]中国原子能科学研究院核物理研究所,北京102413

出　　处：《原子能科学技术》2025年第3期762-768,共7页Atomic Energy Science and Technology

基　　金：国家重点研发计划(2023YFA1607000)。

摘　　要：为了改进传统的人工调束方法,提升其效率和调优品质,本文引入了差分进化(DE)算法,旨在实现调束过程的智能化。在详细阐述差分进化算法的算法架构基础上,采用Python编程语言,并利用py-EPICS接口与实验物理及工业控制系统(EPICS)建立了稳定的连接。此外,为了方便用户操作与监控,建立了直观的控制系统工作室(CSS)界面,实现了高效的上位控制和实时监测功能。本文基于1.7 MV串列加速器平台对DE算法束流调优的可行性和优化效果进行了在线验证。在实验过程中,不仅对算法的性能进行了全面的评估,还根据实验结果对算法进行了针对性的优化和改进。这些改进措施显著提升了算法的优化能力,使得束流传输效率高达80%。本文不仅展示了DE算法在束流调优中的优异性能,还为智能调束技术的发展提供了新的思路和方法。通过实现调束智能化,有望进一步提高加速器系统的运行效率和稳定性,为相关研究和实践领域提供参考。To augment the inherent efficiency and enhance the quality of the conventional manual beam-tuning methodology,this paper presented an innovative approach through the incorporation of a differential evolution(DE)algorithm.Initially,the architectural framework of the DE algorithm was meticulously delineated,serving as the bedrock of the methodological paradigm.The DE algorithm,renowned for its robust optimization capabilities,is implemented utilizing the versatile Python programming language.This implementation leverages Python’s computational prowess and inherent flexibility,enabling the development of a sophisticated algorithmic solution.A resilient connection with the experimental physics and industrial control system(EPICS)was established via the pyEPICS interface.This integration facilitates seamless communication and precise control between the advanced DE algorithm and the intricate accelerator system.The pyEPICS interface acted as a conduit,ensuring real-time data exchange and enabling dynamic adjustments to be made based on the algorithm’s outputs.Furthermore,to augment user operation and monitoring capabilities,an intuitive control system studio(CSS)interface was devised.This interface empowered efficient upper-level control and real-time monitoring functions,thereby significantly bolstering the usability and practicality of the system.The CSS interface features a user-friendly graphical user interface(GUI)that allows operators to monitor and adjust parameters in real-time with ease,enhancing the overall user experience and operational efficiency.Using the 1.7 MV tandem accelerator platform as a testbed,rigorous experiments were conducted to ascertain the feasibility and efficacy of the DE algorithm in beam optimization.These experiments were designed to comprehensively evaluate the algorithm’s performance under various conditions and constraints.During these trials,this paper not only scrutinized the algorithm’s performance but also implemented optimizations and enhancements based on empirical fi

关 键 词：1.7 MV串列加速器 差分进化算法 束流优化 

分 类 号：TL50[核科学技术—核技术及应用]