Skip to main content
QUICK REVIEW

[论文解读] Machine learning prediction of plasma behavior from discharge configurations on WEST

Chenguang Wan, Feda Almuhisen|arXiv (Cornell University)|Feb 22, 2026
Magnetic confinement fusion research被引用 0
一句话总结

该论文开发了基于Transformer的ML代理,以从WEST预放电信号预测六个全局等离子体参数,实现高精度和快速推理。

ABSTRACT

Accurately predicting plasma behavior based on discharge configurations is essential for the safe and efficient operation of tokamak experiments. While physics-based integrated modeling codes provide valuable insights, their high computational cost limits their applicability for fast scenario design and control optimization. In this study, we propose a transformer-based machine learning model to predict key global plasma parameters on the WEST tokamak, including the normalized beta ($β_{n}$), toroidal beta ($β_{t}$), poloidal beta ($β_{p}$), plasma stored energy ($W_{\mathrm{mhd}}$), safety factor at the magnetic axis ($q_{0}$), and safety factor at the 95% flux surface ($q_{95}$). The model uses only signals that can be defined before the discharge, such as magnetic coil currents, auxiliary heating power, plasma current reference, and line-averaged plasma density. Trained on 550 discharges from the WEST campaigns, the model demonstrates an average mean square error (MSE) loss of 0.026, an average coefficient of determination $R^{2}$ of 0.94, and achieves inference times on the order of 0.1 seconds. These results highlight the potential of data-driven surrogate models for assisting in discharge planning, scenario evaluation, and real-time control of tokamak plasmas.

研究动机与目标

  • 从WEST的预放电信号预测六个关键全局等离子体参数:归一化β(βn)、圆环β(βt)、极向β(βp)、等离子体储能(Wmhd)、q0,以及q95。
  • 使用放电前可用的信号(磁线圈电流、辅助加热功率、Ip参考值,以及线密度的平均密度)来构建快速代理模型。
  • 评估多种ML架构,确定在放电预测中表现最佳的模型。
  • 评估模型在550次WEST放电上的泛化能力,并分析对q参数预测的局限性。

提出的方法

  • 对数据进行平滑处理和固定大小滑窗(长度1024、步长512)并进行重叠平均以增强稳定性。
  • 将550次放电分为训练/验证/测试集(60/20/20)。
  • 在MLP、LSTM、Transformer编码器、Transformer解码器以及基于Transformer的贝叶斯超参数优化模型之间进行比较。
  • 基于验证集MSE选择最佳模型,然后报告测试集性能。
  • 报告推理时间并讨论在放电规划和实时控制中的实际适用性。
Figure 1: The Granger causality and Pearson correlation coefficient between input and output signals. For Granger causality, a smaller coefficient indicates a stronger causal relationship, whereas for the Pearson correlation coefficient, a larger value reflects a stronger linear correlation. PowerLH
Figure 1: The Granger causality and Pearson correlation coefficient between input and output signals. For Granger causality, a smaller coefficient indicates a stronger causal relationship, whereas for the Pearson correlation coefficient, a larger value reflects a stronger linear correlation. PowerLH

实验结果

研究问题

  • RQ1前放电、多信号输入集合是否能为WEST预测关键的零维度等离子体参数?
  • RQ2哪种ML架构最能捕捉放电数据中的时序与跨通道相关性?
  • RQ3这些预测的预测精度(MSE、R²)和推理速度能达到怎样的水平?
  • RQ4从预放电信号预测q0和q95的局限性及原因是什么?
  • RQ5模型在多样化的WEST放电集上的泛化能力如何?

主要发现

模型类型均方误差(MSE)损失
多层感知机(MLP)0.0224
长短期记忆网络(LSTM)0.015
Transformer编码器0.011
Transformer解码器0.011
我们基于Transformer的模型0.0096
  • 测试集六个输出的平均MSE为0.026。
  • 测试集上的平均R²为0.94。
  • 基于Transformer的模型在所有测试架构中实现了最低的验证MSE(0.0096)。
  • 所有输入信号都显示出显著的Granger因果关系和皮尔逊相关性,证明了特征相关性。
  • 由于预放电输入对压力/动力学表型的可辨识性较弱以及输入中缺乏压力和动力学信息,q0和q95的预测精度较低。
  • 在RTX 3090和A100两种GPU上,推理时间约为0.1秒。
Figure 2: The workflow of machine learning model in the present work
Figure 2: The workflow of machine learning model in the present work

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。