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

KRONOS-CTRL: The Digital Twin Stack

KRONOS-CTRL is the coupled digital twin that holds a live physics state of each machine and projects it forward as a predictive shadow.

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.

What KRONOS-CTRL is

KRONOS-CTRL is the digital-twin core of L3. It maintains a coherent state vector for the whole machine and advances it faster than real time, so that at any wall-clock instant the twin holds both the best current estimate of plant state and a 50-100 ms forecast of where the state is heading. Four physics modules run inside it and exchange boundary conditions every twin step.

How the modules couple

The modules are not independent. The MHD module fixes the equilibrium and hence the neutron source profile the Neutronics module integrates; Neutronics deposits volumetric heating that the Thermomechanics module turns into strain and temperature; Thermomechanics returns geometry changes (thermal expansion of the vessel, magnet strain via REBCO gauges) that shift the MHD boundary; and for the burner the Power Systems module closes the loop by setting the extraction potential that changes the ambipolar confinement the MHD module sees. KRONOS-CTRL solves this as a weakly coupled fixed-point iteration per twin step, using the previous step as a warm start so one or two Picard passes converge.

Each module is accelerated by an L3 surrogate (a PINN or neural operator) so the coupled step fits inside the shadow latency budget. The twin publishes, every step, a full state estimate, its forward projection, and a per-module confidence score that MPC and the anomaly ensemble consume.

KRONOS-CTRL is instantiated per machine. The breeder twin carries the Grad-Shafranov equilibrium, ELM dynamics and disruption observers; the burner twin carries the ambipolar-potential solve, plug-density balance and the multi-modal DEC train. Both share the same synchronization, surrogate and validation machinery.

Content reviewed August 2026 · design-and-simulation stage