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 › Physical Interfaces
Physical Interfaces

Breeder Sensor-to-Actuator Map

For Hyperion, each control objective is a chain from a diagnostic set to a physical actuator, with the twin and MPC in between.

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.

The breeder control chains

The breeder (Hyperion) runs a D–T spherical tokamak with design-point plasma current 9.66 MA, fusion power 85.0 MW, Qsci 3.076, peak field 16.84 T (8 T on-axis), and negative triangularity δ = −0.30. Every one of those quantities is held by a sensor→actuator chain.

Principal chains

A worked chain

python
# density control chain (breeder)
n_e   = interferometer_lineavg()        # sense (L2 timestamped)
n_ref = campaign_setpoint()             # from L4
u     = density_mpc(n_e, n_ref, twin)   # L3, 50-100 ms shadow
# actuate: L1 splits demand across fast and slow fuelers
gas_puff_valve(u.fast)                  # ms response
pellet_injector(u.slow)                 # deeper deposition

The map is deliberately many-to-many: density is served by three actuators, and one actuator (the PF coils) serves both position and shape. Allocation is resolved by MPC actuator weighting so that reserve is kept on any actuator near a limit.

Because Hyperion is a design-and-simulation study today, each chain is exercised against the digital twin; hardware-in-the-loop commissioning begins after construction start in Q2 2027, and no net-gain is claimed before FOAK first tritium (~2030).

Content reviewed August 2026 · design-and-simulation stage