Physics-Informed Neural Networks for High-Precision Grad-Shafranov Equilibrium Reconstruction

The equilibrium reconstruction of plasma is a core step in real-time diagnostic tasks in fusion research. This paper explores a multi-stage Physics-Informed Neural Networks(PINNs) approach to solve the Grad-Shafranov equation, achieving high-precision solutions with an error magnitude of $O(10^{-8})$ between the output of the second-stage neural network and the analytical solution. Our results demonstrate that the multi-stage PINNs provides a reliable tool for plasma equilibrium reconstruction.