Adapted Swin Transformer-based Real-Time Plasma Shape Detection and Control in HL-3

TL;DR

This paper presents a real-time plasma shape detection method using an adapted Swin Transformer model, enabling fast and accurate feedback for plasma control in HL-3 tokamak under challenging conditions.

Contribution

The study introduces the Poolformer Swin Transformer (PST) model with multi-task learning and knowledge distillation for robust plasma shape detection from CCD images, achieving significant speed and accuracy improvements.

Findings

PST infers R and Z with errors below 1.1 cm and 1.8 cm.

Model processes images in less than 2 ms for real-time feedback.

Successfully deployed in PCS with 500 ms PID control stability.

Abstract

In the field of magnetic confinement plasma control, the accurate feedback of plasma position and shape primarily relies on calculations derived from magnetic measurements through equilibrium reconstruction or matrix mapping method. However, under harsh conditions like high-energy neutron radiation and elevated temperatures, the installation of magnetic probes within the device becomes challenging. Relying solely on external magnetic probes can compromise the precision of EFIT in determining the plasma shape. To tackle this issue, we introduce a real-time, non-magnetic measurement method on the HL-3 tokamak, which diagnoses the plasma position and shape via imaging. Particularly, we put forward an adapted Swin Transformer model, the Poolformer Swin Transformer (PST), to accurately and fastly interpret the plasma shape from the Charge-Coupled Device Camera (CCD) images. By adopting multi-task learning and knowledge distillation techniques, the model is capable of robustly detecting six shape parameters under disruptive conditions such as a divertor shape and gas injection, circumventing global brightness changes and cumbersome manual labeling. Specifically, the well-trained PST model capably infers R and Z within the mean average error below 1.1 cm and 1.8 cm, respectively, while requiring less than 2 ms for end-to-end feedback, an 80 improvement over the smallest Swin Transformer model, laying the foundation for real-time control. Finally, we deploy the PST model in the Plasma Control System (PCS) using TensorRT, and achieve 500 ms stable PID feedback control based on the PST-computed horizontal displacement information. In conclusion, this research opens up new avenues for the practical application of image-computing plasma shape diagnostic methods in the realm of real-time feedback control.