基于多级级联BP神经网络的加速器束流轨道预测  

Accelerator beam orbit prediction based on multi-stagecascaded BP neural networks

作　　者：曹子耕 严春满[1] 杨旭辉 郭玉辉[2] Cao Zigeng;Yan Chunman;Yang Xuhui;Guo Yuhui(College of Physics and Electronic Engineering,Northwest Normal University,Lanzhou 730070,China;Institute of Modern Physics,Chinese Academy of Sciences,Lanzhou 730000,China)

机构地区：[1]西北师范大学物理与电子工程学院,兰州730070 [2]中国科学院近代物理研究所,兰州730000

出　　处：《强激光与粒子束》2023年第12期56-64,共9页High Power Laser and Particle Beams

基　　金：国家重点研发计划项目(2022YFF0704900);中国科学院先导专项B类(XDB25030103);甘肃省重点研发计划工业类项目(23YFGA0013)。

摘　　要：加速器束流轨道校正对于加速器稳定运行具有非常重要的作用,精确预测加速器束流轨道的变化对于实现束流自动化校准也具有重要意义。通过对束流轨道变化的准确预测,可以为调整加速器控制参数提供可靠的信息,从而实现对束流的精确控制和调节。通过研究束流在直线加速器中等能量传输段的传输过程,利用模拟加速器数据,基于多级级联的反向传播(BP)神经网络搭建了加速器束流轨道预测模型,能够实现对束流轨道参数的预测。结果表明,与采用传统单隐层BP神经网络建立的预测模型相比,多级级联BP神经网络能够实现更高的预测精度与可靠性,为直线加速器中等能量传输段的优化设计和束流轨道自动化校准提供了一种有效的方法。Since accelerator beam orbit correction is crucial for stable operation of accelerators,accurateprediction of the changes of the accelerator beam orbit is also essential for automated beam calibration.Precisepredictions of beam orbit changes can provide reliable information for adjusting accelerator control parameters toachieve 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 sectionof a linear accelerator is studied and an accelerator beam orbit prediction model is constructed to predict beam orbitparameters.The results show that the proposed multi-stage cascaded BP neural network achieves higher predictionaccuracy and reliability than the prediction model built using a traditional single hidden layer BP neural network.Thisprovides an effective method for optimally designing the medium energy transfer section of the linear accelerator andautomating the calibration of the beam orbit.

关 键 词：加速器驱动次临界系统 中等能量传输段 级联网络 反向传播神经网络 束流轨道预测 

分 类 号：TL81[核科学技术—核技术及应用] TP183[自动化与计算机技术—控制理论与控制工程]