| 托卡马克中由线积分数据重建分布的神经网络方法 |
| |
| 引用本文： | 朱思铮,张磊.托卡马克中由线积分数据重建分布的神经网络方法[J].计算物理,1996,13(3):283-288. |
| |
| 作者姓名： | 朱思铮 张磊 |
| |
| 作者单位： | 中国科学院等离子体物理研究所, 合肥 230031 |
| |
| 摘 要： | 用多层前馈神经网络,处理托卡马克中由物理量沿观察弦的线积分值重建其空间分布的反演问题。用BFGS拟牛顿法大大加快了标准误差反向传播算法(BP)的收敛速度
|
| 关 键 词： | 线积分值 分布重建 神经网络 BFGS拟牛顿法 |
| 收稿时间： | 1995-03-17 |
| 修稿时间： | 1995-12-26 |
RECONSTRUCTION OF PROFILE FROM LINE INTEGRAL DATE USING NEURAL NETWORK IN TOKAMAKS |
| |
| Zhu Sizheng,Zhang Lei.RECONSTRUCTION OF PROFILE FROM LINE INTEGRAL DATE USING NEURAL NETWORK IN TOKAMAKS[J].Chinese Journal of Computational Physics,1996,13(3):283-288. |
| |
| Authors: | Zhu Sizheng Zhang Lei |
| |
| Institution: | Institute of Plasma Physics, Academia Sinica, Hefei 230031 |
| |
| Abstract: | Amultilayer feedforward neural network is used to reconstruct spacial distribution from line integral data along survey chords through the plasma in tokamaks. The BFGS quasi-Newton algorithm is employed to accelerate the convergence of standard error backpropagation (BP) greatly. |
| |
| Keywords: | line integral data reconstruction of profile neural network BFGS quasi-New ton algorithm |
| 本文献已被 维普 等数据库收录！ |
| 点击此处可从《计算物理》浏览原始摘要信息 |
| 点击此处可从《计算物理》下载免费的PDF全文 |
