Physics Informed Neural Networks towards the real-time calculation of heat fluxes at W7-X
Nuclear Materials and Energy(2023)
摘要
•Monitoring the heat flux in real-time is pivotal for steady-state fusion operation.•Existing 2D codes for heat flux estimation, such as THEODOR, are only employed offline.•A Physics-Informed Neural Network (PINN) can solve the heat equation.•The PINN is fully differentiable and can be natively run on a GPU.•The PINN is compared with THEODOR.
更多查看译文
关键词
heat fluxes,physics,networks,real-time
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要