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 › The Master Blueprint
The Master Blueprint

The Stack and the DEC Train

How the architecture controls the burner's multi-modal direct-energy-conversion train — TWDEC, ultra-high-field MHD, and thermionic stages.

STRATEGY / SLOW ▲ ▼ MICROSECOND REAL-TIMEL7Ecosystem & Strategytelemetry ▲ control ▼open ▸L6Experience & Visualizationtelemetry ▲ control ▼open ▸L5Applications & Copilotstelemetry ▲ control ▼open ▸L4Orchestrationtelemetry ▲ control ▼open ▸L3Twin Modeling & AItelemetry ▲ control ▼open ▸L2Data Fabrictelemetry ▲ control ▼open ▸L1Control Planetelemetry ▲ control ▼open ▸L0Foundationtelemetry ▲ control ▼open ▸PHYSICAL S.M.A.R.T. GENERATOR PLANTBREEDER · HYPERION1R0 1.2 m · A 2.5 · 16.84 T · δ −0.30BURNER · TANDEM MIRROR2317 T throat · 26.49 T plug · fₙ 5.44% · DEC1 center stack + plasma · 2 high-field plug · 3 expander → direct converterCOLOR GRAMMAR strategy AI-workflow infra/data models reactor/DECLINE SEMANTICStelemetry (µs)controlKRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORMASTER BLUEPRINTSHEET 01REV. 2026-08L0-L7 · 2 MACHINES
The AI-Native S.M.A.R.T. Generator Master Blueprint — eight layers (L0→L7), one control stack, wired to both machines. Telemetry rises in microseconds; control descends the same path.

Converting output directly

On the burner, the direct-energy-conversion (DEC) train is where the plasma's charged-particle output becomes usable energy without a conventional thermal cycle for that fraction. It is a multi-modal train, and the architecture controls it as an orange reactor/thermal path with its own diagnostics and actuation.

The stages

The control problem

DEC control is coupled to plasma control: the flux and energy spectrum entering the train depend on the end-plug density and the ambipolar potential upstream. The MPC agent must therefore steer the escaping charged particles into the train's acceptance window while the plasma loop holds the plug — a single coordinated objective across L3.

Why it is a shared-stack module, not a new stack

The DEC train is unique to the burner, but it does not need a new architecture. It is a set of L2 diagnostics, an L3 twin sub-model, and L1 actuation — the same layers, pointed at conversion instead of confinement. This is the one-architecture principle applied to the output end of the machine.

Multi-modal by design

The three stages are complementary because the escaping population is not monoenergetic. TWDEC recovers the fast directed ions most efficiently; the ultra-high-field MHD stage handles the bulk flow; thermionics captures residual heat that the first two stages leave behind. The twin models the energy spectrum entering the train so the MPC agent can bias operation toward whichever stage matches the current output — a conversion-side optimization that mirrors the confinement-side optimization on the breeder.

DEC control sits inside the burner control problems and is executed within the command boundary.

Content reviewed August 2026 · design-and-simulation stage