束晕-混沌的神经网络自适应控制
Control of beam halo-chaos using neural network self-adaptation method
-
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。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 selfadaptation method. The envelope radius of highintensity 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 halochaos is obviously suppressed and amplitude shake is largely reduced when the neural network self-adaptation control is applied．
-
点击查看大图
计量
- 文章访问数: 2269
- HTML全文浏览量: 194
- PDF下载量: 495
- 被引次数: 0
下载:
