• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Plasma physics and controlled fusion >Neural network based prediction of no-wall beta(N) limits due to ideal external kink instabilities
【24h】

Neural network based prediction of no-wall beta(N) limits due to ideal external kink instabilities

机译：基于神经网络的无墙Beta（n）限制的预测由于理想的外部kink稳定性

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Multi-layer perceptron based neural networks (NNs) are trained to predict the Troyon no-wall beta limits due to the onset of low-n (n = 1-3, n is the toroidal mode number) ideal external kink instabilities in tokamak plasmas. It is found that a well trained NN can predict the n = 1 no-wall beta limit within 10% relative error. The NN performance is somewhat worse for the n = 2 and 3 no-wall beta limits, but still a relative error within 20% is achievable. The trained NNs well reproduce the known dependences of the no-wall beta limits on the plasma pressure (pressure peaking factor) and current (plasma internal inductance) profiles. Other scalings are also easily established with NNs, for parametric dependences such as on the aspect ratio, the elongation and triangularity of the plasma boundary shape. The results show that the semi-analytically generated training database can be used to train NNs for predicting the no-wall limit in realistic experiments. These NN-based Troyon beta limit predictors can be incorporated into integrated modeling platforms, or directly implemented as a real time stability estimator for the purpose of disruption avoidance or mitigation during experiments.
机译：基于基于的基于Mactceptron的神经网络（NNS）被训练，以预测由于低N（n = 1-3，n是环形模式编号）理想的外部Kink不稳定性导致的TROYON无壁测试限制.TOKAMAK等离子体。发现训练良好的NN可以在10％相对误差内预测n = 1无壁β限制。对于n = 2和3个无墙测试限制，NN性能有点差，但仍有20％的相对误差是可实现的。训练的NNS良好地再现了无壁β限制对等离子体压力（压力峰值因子）和电流（等离子体内部电感）轮廓的已知依赖性。对于参数依赖性，例如在纵横比，等离子体边界形状的伸长和三角形，也容易建立其他缩放。结果表明，半分析生成的训练数据库可用于训练NNS，以预测现实实验中的无壁限制。这些基于NN的Troyon Beta限制预测器可以被纳入集成的建模平台，或者直接实现为实际稳定估计器，以便在实验期间减轻避免或缓解。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号