| 束晕-混沌的神经网络自适应控制 |
| |
| 引用本文： | 黄国现,罗晓曙,方锦清. 束晕-混沌的神经网络自适应控制[J]. 强激光与粒子束, 2004, 16(9): 1191-1194 |
| |
| 作者姓名： | 黄国现 罗晓曙 方锦清 |
| |
| 作者单位： | 1. 广西师范大学 物理与信息工程学院, 广西 桂林 541004; 2. 中国原子能科学研究院, 北京 102413 |
| |
| 基金项目： | 国家自然科学基金资助课题(10247005,70070147);广西"新世纪十百千人才工程"人选专项基金资助课题(2002226) |
| |
| 摘 要： | 理论分析了强流离子束在周期磁场聚焦通道中传输时产生的束晕 混沌动力学行为,给出了近似反映实际聚焦磁场的余弦函数形式。然后利用神经网络方法对非线性复杂系统控制的优越性,提出前馈反传神经网络方法对强流离子束中束晕 混沌进行自适应控制。通过适当选择的神经网络控制结构和线性反馈系数以及自适应调整神经网络的权系数,可将强流离子束的包络半径达到束匹配半径的控制目标,且束包络的抖动大小明显减少,束晕 混沌现象得到了明显的抑制。
|
| 关 键 词： | 束晕-混沌 强流离子束 神经网络自适应控制 |
| 文章编号： | 1001-4322(2004)09-1191-04 |
| 收稿时间： | 2003-12-03 |
| 修稿时间： | 2003-12-03 |
Control of beam halo-chaos using neural network self-adaptation method |
| |
| huang guo-xian,luo xiao-shu,fang jin-qing. Control of beam halo-chaos using neural network self-adaptation method[J]. High Power Laser and Particle Beams, 2004, 16(9): 1191-1194 |
| |
| Authors: | huang guo-xian luo xiao-shu fang jin-qing |
| |
| Affiliation: | 1. College of Physics and Information Engineering, Guangxi Normal University, Guilin 541004,China;2. China Institute of Atomic Energy, P. O. Box 275-81, Beijing 102413, China |
| |
| Abstract: | Taking the advantages of neural network control method for nonlinear complex systems, control of beam halo-chaos in the periodic focusing channels of high intensity accelerators is studied by feed-forward back-propagating neural network self-adaptation method. The envelope radius of high-intensity proton beam can reach the matched beam radius by selecting suitable control structure of neural network and the linear feedback coefficient, and adjusting the right-coefficient of neural network. The beam halo-chaos is obviously suppressed and amplitude shake is largely reduced when the neural network self-adaptation control is applied. |
| |
| Keywords: | Beam halo-chaos High intensity proton beam Neural network self-adaptation control |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《强激光与粒子束》浏览原始摘要信息 |
|
点击此处可从《强激光与粒子束》下载免费的PDF全文 |
