Skip to content
Technology How it works Breeder — Hyperion Burner — Aegis Burner — MetroVolt AI-Native Architecture Magnets Fuel cycle Safety Roadmap
Solutions AI & Data Centers Defense & Government Grid & Baseload Neutron Detection Quantum
Learn Technical Library
Proof Publications Whitepapers Technical Library Open Science & Reproducibility The Honest Gates
Company About / Mission Leadership Environment Health & Safety Investors Careers Press Contact
3D Model
AI Architecture › L3 · Twin Modeling & AI
L3 · Twin Modeling & AI

L3 for the Burner: End-Plug Density

For the tandem-mirror burner, confinement stands or falls on end-plug density, and L3's central task is to hold it against a fast collapse mode.

THE STACK · click to jumpL7Ecosystem & StrategyL6Experience & VisualizationL5Applications & CopilotsL4OrchestrationL3Twin Modeling & AIL2Data FabricL1Control PlaneL0Foundation▲tlmctl▼L3 · TWIN MODELING & AIThe KRONOS-CTRL digital twin and its predictive shadow.1KRONOS-CTRL Twinlive plant state2GNNscoupled subsystems3PINNsphysics-constrained4Anomaly Ensemblesdrift & fault detection5MPCreceding-horizon control6Predictive Shadowruns seconds aheadMACHINE TIEState estimate descends to L1 control; alerts rise to L4 / L5.KRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORTWIN MODELING & AISHEET 05REV. 2026-08L3 · AI-NATIVE STACK
L3 · Twin Modeling & AI — its place in the stack (left, click any layer) and its internal components (right). Telemetry rises; control descends.

The burner's defining control problem

The D-3He tandem-mirror burner confines its central cell with an ambipolar potential set by dense end plugs at 26.49 T (17 T throat). Plug density is therefore the master control variable: it sets the confining potential, which sets central-cell confinement, which sets fusion output. Where the breeder's core problem is equilibrium, the burner's is holding plug density in the window that sustains the potential.

How L3 holds it

The ambipolar-potential PINN predicts how plug fueling, heating, and DEC collector potentials move the plug density and the confining potential; plug-density MPC drives those actuators to the target; the stability analysis checks mirror/interchange margins; the shadow projects the potential 50-100 ms ahead. The Power Systems module couples in because the DEC potentials are both an actuator and the confinement boundary.

The dangerous mode is fast: if plug density falls, the confining potential erodes and central-cell confinement can collapse in tens of milliseconds, faster than a from-scratch MPC replan. Kronos precomputes plug-recovery maneuvers triggered on an anomaly-ensemble precursor (a potential or plug-density signature departing from the shadow), so recovery begins before confinement is lost.

As a design/simulation study pre-FOAK, plug-density control is validated against high-fidelity mirror-confinement models; the burner is a later program element than the breeder, and no net-gain is claimed from this control before hardware. The framework mirrors the breeder's, same PINN/MPC/anomaly machinery, applied to a different confinement physics.

Content reviewed August 2026 · design-and-simulation stage