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 › L6 · Experience
L6 · Experience

Diagnostic Health Mosaic

A single glanceable map of the 60+ diagnostic ports — which are healthy, degraded, dead, or imputed — because everything the operator trusts rests on this.

THE STACK · click to jumpL7Ecosystem & StrategyL6Experience & VisualizationL5Applications & CopilotsL4OrchestrationL3Twin Modeling & AIL2Data FabricL1Control PlaneL0Foundation▲tlmctl▼L6 · EXPERIENCE & VISUALIZATIONHow people see, steer, and review the plant.1Control-Room 3D Twinlive overlays2Plant-Floor SCADAoperations HMI3Mobile Engineeringfield access4Alerting UXtriage & escalation5DashboardsKPIs & health6Replayincident reviewMACHINE TIESurfaces the L3 twin state and L5 copilots to human operators.KRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATOREXPERIENCE & VISUALIZATIONSHEET 08REV. 2026-08L6 · AI-NATIVE STACK
L6 · Experience & Visualization — its place in the stack (left, click any layer) and its internal components (right). Telemetry rises; control descends.

The foundation under every other number

Every estimate, KPI, and forecast on every L6 surface ultimately rests on the diagnostics feeding the twin. If an operator does not know which sensors are healthy, they cannot properly weight anything downstream. The diagnostic health mosaic is a compact map of the machine's 60+ diagnostic ports — Mirnov coils, flux loops, interferometry, Thomson scattering, neutron detectors, REBCO strain gauges, and more — each colored by health so the whole measurement front is readable at a glance.

Four states per diagnostic

StateMeaning for downstream trust
Healthymeasured, full weight
Degradednoisy or drifting; reduced weight, wider bands
Deadno signal; masked, excluded from estimates
Imputedreconstructed by the GNN from neighbors; flagged everywhere

Fusion diagnostics degrade under neutron and thermal load, so this map is dynamic and consequential. When a Mirnov coil drops and the GNN imputes it, the mosaic shows the port as imputed, and that state propagates: the equilibrium estimate's provenance names the imputation, its confidence widens, and the affected overlay region shows hatching. The mosaic is where the operator first sees the cause of a confidence change elsewhere.

Trend, not just snapshot

The mosaic shows not only current state but degradation trend, so an operator can see a diagnostic drifting toward failure and plan around it before it is lost mid-shot. Calibration-drift tracking feeds this view, distinguishing a genuine physics change from an instrument going out of calibration. For both machines, sustained diagnostic-availability is a first-order KPI precisely because it gates trust in everything else.

The mosaic is the operator-facing face of signal validation and GNN imputation from L2/L3, and it directly drives confidence and provenance and the hatching in the 3D overlay. Its availability metric appears on the dashboards.

Content reviewed August 2026 · design-and-simulation stage