Regulation Compliant AI for Fusion: Real-Time Image Analysis-Based Control of Divertor Detachment in Tokamaks

TL;DR

This paper presents a real-time, interpretable AI control system for divertor detachment in tokamaks, demonstrating precise feedback control using image diagnostics, suitable for regulatory environments in fusion reactors.

Contribution

It introduces a linear, interpretable AI control framework for fusion diagnostics, enabling regulatory compliance and real-time feedback control in tokamak divertor management.

Findings

Achieved 2% mean absolute difference in detachment control

Validated real-time AI control with DIII-D camera data

Framework applicable to various image-based diagnostics

Abstract

While artificial intelligence (AI) has been promising for fusion control, its inherent black-box nature will make compliant implementation in regulatory environments a challenge. This study implements and validates a real-time AI enabled linear and interpretable control system for successful divertor detachment control with the DIII-D lower divertor camera. Using D2 gas, we demonstrate feedback divertor detachment control with a mean absolute difference of 2% from the target for both detachment and reattachment. This automatic training and linear processing framework can be extended to any image based diagnostic for regulatory compliant controller necessary for future fusion reactors.