FOR EVALUATIONDOC TORUS-AI-001REV 2026-07 CLASS Unattended Facility Sensing / AI-ML enginePacketFive
TORUS AI/ML Engine

Facility awareness at every tier of the sensing chain.

TORUS detects, classifies, and prioritises facility security events for AI/HPC data centers. Machine learning runs where the data is born: on the node, at the gateway, and in the operations layer. Each tier turns raw signal into a smaller, more certain facility event, so what travels the network and reaches the operator is a classified track, not a raw feed or a bare alarm.

01 / WHY AI, NOT THRESHOLDS

A tripwire counts; an engine understands

Classify

Type, not just presence

Footfall, vehicle, digging, generator vibration, or handling noise. The system reports what it is, with a confidence, not merely that something happened.

Corroborate

Fuse across domains

A seismic cue plus an acoustic cue from a neighbouring node is a stronger facility-security track than either alone. Fusion is where confidence is earned.

Suppress

Fewer false alarms

Wind, rain, traffic, wildlife, and facility maintenance are the main false-alarm sources for an unattended sensor. On-device models learn the background and suppress nuisance alarms.

02 / THREE TIERS OF FACILITY AWARENESS

Edge, gateway, operations

AI is distributed, not centralised. Every tier runs the inference its power and vantage allow, and passes a smaller, richer event to the next.

TIER 1 · EDGE / NODE

On-device TinyML

  • Seismic and acoustic classification on the ESP32-S3, quantized for a battery budget
  • Hardware wake-on-seismic, then an ML pass confirms and classifies before any radio use
  • Event vs background discrimination cuts the message rate and the power bill
  • Audio is classified at the node; raw audio never leaves it
ESP32-S3 · QUANTIZED TinyML
TIER 2 · GATEWAY / MEG

Accelerated edge inference

  • NVIDIA Jetson Orin runs thermal and visual inference on cued imagery from the masts
  • Detect, track, and classify at the gateway, so backhaul carries decisions, not video
  • Multi-node fusion across the local ring before anything leaves the site
JETSON ORIN · THERMAL / VISUAL / FUSION
TIER 3 · OPERATIONS / CCISRT

Correlation & tracks

  • Clusters corroborating events across nodes into a single track with aggregate confidence
  • Classification fusion, operating-pattern analysis, and false-alarm suppression across the whole facility
  • Explainable rule-based correlator today; a learned model drops in behind the same interface
CCISRT · CORRELATION / TRACKING / API
03 / THE FACILITY EVENT PIPELINE

Raw signal in, decision out

SENSE

Raw signal

Geophone, microphone, thermal, LiDAR, RF at the node.

CLASSIFY

Edge TinyML

Node labels the event and its confidence; discards background.

FUSE

Gateway

Corroborate across the local ring; run visual inference on cue.

CORRELATE

Operations

Form tracks across the facility; suppress false alarms.

DECIDE

Operator

A classified track with location and confidence, ready to act on.

Each stage reduces data and raises certainty. A raw waveform becomes a labelled event, a set of events becomes a track, and a track becomes a decision, so the network carries kilobytes of event data rather than megabytes of feed.

04 / MODELS & METHOD

How the models are built and run

TierRuntimeApproach
EdgeESP32-S3, no acceleratorSmall quantized classifiers (TinyML) sized to RAM and the battery budget; wake-gated so inference runs only on a real cue
GatewayNVIDIA Jetson OrinAccelerated detection / tracking on thermal and visual streams; on-site so raw imagery stays local
OperationsCCISRT serverRule-based correlation today (explainable, auditable); learned multi-target tracking and classification fusion drop in behind the same track interface
All tiersIsaac SimFacility scenarios generate labelled data and validate detection and false-alarm rates before deployment trials

Explainable first. The operations correlator ships as transparent rules so an operator can see why a track formed. Learned models are introduced behind that interface, with the rule-based path retained as a fallback and a sanity check.

05 / DATA GOVERNANCE & FACILITY PRIVACY

Classify at the source, keep raw data local

Privacy

Raw stays put

Audio and imagery are processed where captured; only compact labelled events cross the network.

Bandwidth

Less on the wire

Sending decisions instead of feeds cuts bandwidth and power while keeping facility networks focused on compact event data.

Assurance

Auditable inference

Track formation and operations actions are logged, so an analyst can reconstruct why the system decided what it did.

06 / ROADMAP

From rules to learned fusion

NowNext
On-device seismic / acoustic classification at the nodeLarger vocabularies and per-site adaptation via OTA model updates
Rule-based correlation and track formation at the operations layerLearned multi-target tracking and cross-domain classification fusion behind the same interface
Isaac Sim facility scenario data for validationActive learning from operator confirmations to cut false alarms over time
TIA-942 and OCP-aligned event evidenceNorthbound integration API adapters for PSIM, DCIM, BMS, VMS, SIEM, and Redfish
TRADEMARKS & THIRD-PARTY NOTICE

TORUS is an independent platform. Company names and product model numbers referenced in this document (including but not limited to Espressif ESP32-S3 and NVIDIA Jetson, Orin, and Isaac Sim) are used solely for engineering and bill-of-materials identification and imply no affiliation with or endorsement by those companies. Supply of any such third-party product to the designers, integrators, or evaluators of the TORUS platform remains at the sole discretion of the respective owning company, organisation, or legal entity. PacketFive Design Services can adapt TORUS AI/ML models and integrations for other customer requirements. "FOR EVALUATION" is a document-handling marking only and denotes no security classification. All trademarks are the property of their respective owners.