Reconstruction of poloidal magnetic field profiles in field-reversed configurations with machine learning in laser-driven ion-beam trace probe

The diagnostic of poloidal magnetic field (${B}_{\mathrm{p}}$) in field-reversed configuration (FRC), promising for achieving efficient plasma confinement due to its high β, is a huge challenge because ${B}_{\mathrm{p}}$ is small and reverses around the core region. The laser-driven ion-beam trace probe (LITP) has been proven to diagnose the ${B}_{\mathrm{p}}$ profile in FRCs recently, whereas the existing iterative reconstruction approach cannot handle the measurement errors well. In this work, the machine learning approach, a fast-growing and powerful technology in automation and control, is applied to ${B}_{\mathrm{p}}$ reconstruction in FRCs based on LITP principles and it has a better performance than the previous approach. The machine learning approach achieves a more accurate reconstruction of ${B}_{\mathrm{p}}$ profile when 20% detector errors are considered, 15% ${B}_{\mathrm{p}}$ fluctuation is introduced and the size of the detector is remarkably reduced. Therefore, machine learning could be a powerful support for LITP diagnosis of the magnetic field in magnetic confinement fusion devices.