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 › L4 · Orchestration
L4 · Orchestration

Plug-Stability Supervision

The burner's tandem-mirror end plugs must hold continuously; orchestration supervises plug field and stability and gates every corrective setpoint.

THE STACK · click to jumpL7Ecosystem & StrategyL6Experience & VisualizationL5Applications & CopilotsL4OrchestrationL3Twin Modeling & AIL2Data FabricL1Control PlaneL0Foundation▲tlmctl▼L4 · ORCHESTRATIONEvents, workflows, rules, and human routing.1Event Streamingthe backbone2Workflow Enginecampaign procedures3Rules & Safety Boundshard limits4Human-in-the-Loopapproval routing5Schedulerexperiment campaigns6Audit Busfull decision lineageMACHINE TIECoordinates L3 outputs with L5 copilots and human operators.KRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORORCHESTRATIONSHEET 06REV. 2026-08L4 · AI-NATIVE STACK
L4 · Orchestration — its place in the stack (left, click any layer) and its internal components (right). Telemetry rises; control descends.

The plug is the burner's crux

The burner (Aegis / MetroVolt) is a D-3He tandem mirror whose end plugs (design field 26.49 T, throat 17 T) confine the central-cell plasma. Losing plug confinement ends the operating point. In steady state, orchestration runs a continuous plug-stability supervisor that watches plug field, mirror ratio, and stability indicators and issues small corrective setpoints through the full gating pipeline.

Supervisory loop

python
while state == STEADY_STATE:
    s = twin.reconstruct()                     # plug field, mirror ratio, beta
    if s.stability_margin < MARGIN_WARN:
        prop = copilot.correction(s)           # proposed plug/throat setpoint nudge
        cmd  = reconcile(prop, twin.predict(prop))
        gate(cmd)                              # schema+rules+envelope+rate
    if s.stability_margin < MARGIN_CRIT:
        safe_bleed()                           # rate-limited controlled shutdown

Envelope in plug space

The envelope checker for the burner is expressed in plug-relevant coordinates: the joint region of plug field, throat field, mirror ratio, and beta that keeps confinement and stays within magnet ratings. A setpoint that individually looks fine but pushes the mirror ratio combination toward a loss-of-confinement boundary is rejected.

Two failure directions

Continuous, checkpointed, simulated

Supervision is a long-running procedure that checkpoints continuously so a supervisor restart resumes without dropping the plug. As a design-and-simulation study with no built machine and no net-gain claim, plug supervision is validated against long-duration twin runs and fault injection.

Content reviewed August 2026 · design-and-simulation stage