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 › L1 · Control Plane
L1 · Control Plane

Hardware-in-the-Loop Commissioning

Before either machine energizes, L1 is validated against the digital twin in hardware-in-the-loop tests that exercise every loop and failsafe deterministically.

THE STACK · click to jumpL7Ecosystem & StrategyL6Experience & VisualizationL5Applications & CopilotsL4OrchestrationL3Twin Modeling & AIL2Data FabricL1Control PlaneL0Foundation▲tlmctl▼L1 · CONTROL PLANEHard real-time actuation and the autonomous failsafe.1Edge FPGAµs-determinism2Real-Time Actuationcoils · heating · fuel3Hardware Failsafeautonomous trip4Sync Gatephase-locked timing5Signal I/OADC / DAC6Watchdogliveness & interlocksMACHINE TIEDrives magnets, ice-piston, and gas puff on the sub-10 µs loop.KRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORCONTROL PLANESHEET 03REV. 2026-08L1 · AI-NATIVE STACK
L1 · Control Plane — its place in the stack (left, click any layer) and its internal components (right). Telemetry rises; control descends.

Proving the control plane before first plasma

Both machines are, today, design and simulation studies; construction of the breeder begins Q2 2027, with first-of-a-kind first tritium around 2030. Long before energization, the control plane must be proven. Kronos validates L1 with hardware-in-the-loop (HIL) testing: the real FPGA controllers, drivers, and interlocks run against the digital twin standing in for the plasma and plant.

What HIL exercises

Fault injection is central: HIL deliberately drops channels, faults DEC stages, stalls controllers, and withholds MPC targets to confirm that watchdogs fire, redundancy votes, ride-through holds, and the machine defaults safe. A failsafe is only trustworthy once it has been made to act in test.

Closing the analytic loop

HIL confirms that the certified bounds are real. Measured latency and jitter must agree with the WCET and jitter budgets; where they diverge, the design is corrected before hardware energizes. This is how the paper guarantees of the deterministic layer become validated guarantees.

From twin to machine

Because the same digital twin used in HIL later runs as the operating L3 shadow, commissioning and operation share a model lineage: the control plane is tested against the same physics it will later be advised by. HIL is the bridge from simulation study to a machine whose control plane is trusted from first energization onward.

Content reviewed August 2026 · design-and-simulation stage