Operator portal

Machine health and uptime

Live-style monitoring for every unit: channels, compressor, calibration, connectivity, throughput and revenue.

Simulated real-world data being used for demonstration purposes

Sites

Sessions today

148

Revenue today

£412

Uptime

99.2%

Queue

0

168s average session

AIR-BRISTOL-01 · online
Connectivityethernet · 74%
Compressor96%
Enclosure temp18°C
CalibrationVALID
Leak testPASS
RetractorsOK
PaymentOK
Firmware2.7.1
Service due62 days
Hours24 hours

FL

21,430 cycles

FR

20,980 cycles

RL

22,110 cycles

RR

21,870 cycles

Evidence base

Why a forecourt operator should care

The commercial case sits on documented demand: a very large share of vehicles arriving on any forecourt are already outside specification.

The addressable problem is on the site already

UK survey data puts 57% of cars 10% or more below their recommended pressure, and roadside observation studies in other markets show the same pattern.2024,2001

Drivers want help, not equipment

37% of drivers report low confidence inflating their own tyres, which is why a guided four-hose session converts where a coin-operated hose does not.2024

Volume context

Roughly 50 million new tyres enter the UK each year, and European replacement volumes run in the hundreds of millions - the forecourt sits directly upstream of that spend.2025,2026

A safety story worth publishing

Tyre-related casualty and MOT failure statistics give a site operator a measurable public-good claim, not a marketing one.2025,2026

These are published third-party sources, not AiR simulation. The full bibliography - peer-reviewed papers, reference monographs, government reports, international standards and official statistics - lives in the science lab.

Open the research and full bibliography

Edge session, synchronised

Node compute, connectivity and federated rounds

Per-node allocation and round behaviour for the currently modelled edge session, shared with the simulator, the digital twin and the fleet portal.

F1 · Jetson Orin NXFull cloud-connectedMains, nominal thermals1,000 nodes62% host share cap45% duty cycle

Available per node

157TOPS

157 TOPS peak, power derated

Safety reservation

43.9TOPS

Never pre-empted

Shared compute

97.3TOPS

62% of the node

Fleet useful capacity

141,200TOPS

0.0455% of the 100 MW reference

Scheduler allocation

Tyre-safety control looprunning18.9 TOPS
On-unit local intelligencerunning25 TOPS
Federated fine-tuningrunning40.8 TOPS
Scheduled tenant inferencerunning56.5 TOPS

Federated round in this session

Participating nodes947
Queued for later delivery53
Aggregate delta volume246.2 MB
Round duration6.1 min
Rounds per day59
Fleet compute draw36 kW
  • A host share above 60 percent should be contracted with an explicit thermal, power and privacy schedule.

Federated learning behaviour

Local trainingFine-tuning runs on data that never leaves the node or its regional trust boundary.
Update extractionOnly model updates or anonymised aggregates are transmitted, never raw vehicle or user records.
Secure aggregationRegional anchors aggregate updates so the control plane cannot attribute an update to one node.
Differential privacyNoise is added where a research use case justifies it, at the cost of some model fidelity.
National reconstructionThe central model is reconstructed from aggregates and redistributed as a signed package.
Tenant isolationExternal compute tenants run in separate namespaces with no route to vehicle, driver or safety data.

Data flow, stage by stage

  1. 01

    Sense · Node, L0

    Pressure, temperature, valve state and session context captured at the channel. Raw sensor data never leaves the enclosure in raw form.

  2. 02

    Decide locally · Node, L1

    The deterministic engine selects an approved profile, applies the thermal allowance and safety clamp, and drives the channels. No network dependency exists at this stage.

  3. 03

    Infer and redact · Node, L2

    Onboard inference runs anomaly, leak-pattern and integrity checks, then the redaction pipeline strips identifiers and derives features before anything is queued for transport.

  4. 04

    Sign and classify · Node, L2

    The session record is signed with the device key and each outbound message is tagged P0 to P4, which fixes its transport, priority and residency for the rest of its life.

  5. 05

    Transport by class · L3

    P0 and P1 take whichever path is available, LoRa included. P2 to P4 wait for IP. Bulk traffic is deferred to off-peak windows and never touches the resilience plane.

  6. 06

    Broker regionally · Anchor, L4

    Anchors cache models, broker compute work units, forward Reticulum traffic and hold store-and-forward queues for nodes that are currently unreachable.

  7. 07

    Reconcile centrally · Control plane, L5

    Signed sequence numbers and idempotent processing mean queued events replay safely when IP returns. Duplicate delivery over two planes is expected and harmless.

  8. 08

    Aggregate and serve · L6

    Personal records land in the UK sovereign service, anonymised trends in the analytics plane, tenant outputs in an isolated namespace. The three are never joined.

Adjust this session in the edge workload simulator

Uptime is the product

Channel health, calibration windows and throughput in one view.

/Uptime/Throughput/Revenue per bay/Consumables/Remote diagnostics/Service windows/Uptime/Throughput/Revenue per bay/Consumables/Remote diagnostics/Service windows

Operator economics

A forecourt asset that reports on itself

For the site operator the question is simple: does this bay earn more than the air line it replaces, and how often will someone have to attend it?

Machine uptime

0.0%

Sessions per day per unit

0

Mean time to diagnose

0 min

Remote diagnostics before any van is dispatched.

Scheduled attendance

0 /yr

Calibration and consumable replacement.

Every valve cycle, retractor pull and compressor hour is counted. Components are replaced on condition and cycle count rather than after a failure that closed the bay.

  • Per-channel valve and transducer cycle counts
  • Compressor duty and reserve trend
  • Hose retractor wear projection
  • Remote firmware and profile updates during quiet hours

Questions

Straight answers

A power feed, a network connection and a bay footprint comparable to an existing air and water point. Compressed air is generated internally.
AiR, under the modelled service agreement, with remote diagnostics first and scheduled attendance for calibration and consumables.