Fleet portal

Compliance at scale

Every AiR session becomes a compliance record: which vehicles are correct, which need attention, and which show repeat pressure loss.

Simulated real-world data being used for demonstration purposes

Verified Care compliance

Not enrolled

A verified four-channel check every 90 days is what keeps tyre warranty cover claimable across the fleet. Status below is derived from sessions completed in this platform.

Verified checks, last 12 months0 of 4

Next check dueFirst check required to enrol

Last verified checkNone recorded

What compliance recovers

Shoulder and inner-edge wearClaimable once inflation is excluded as a cause

Mileage guarantee shortfallEnforceable pro-rata against tread remaining

Cord or wire exposureReferable with a loss-pattern history behind it

Load-related wear on EVs and vansPriced against declared load, not a nominal case

Duty of careTimestamped per-wheel evidence per vehicle, per quarter

The tyre warranty standard

Fleet vehicles

1,284

Checked this month

1,031

Compliant

92%

Critical

71 need attention

Vehicle	Type	Depot	Driver	Duty cycle	Avg correction	Last check	State
FL20 ABC	Van	Manchester	J. Bennett	Urban multidrop	1.1 PSI	0d	critical
FL21 BCD	EV van	Preston	S. Okafor	Trunking	1.5 PSI	1d	compliant
FL22 CDE	Car	Leeds	R. Ahmed	Regional	1.9 PSI	2d	compliant
FL23 DEF	EV car	Birmingham	L. Novak	Depot shuttle	2.3 PSI	3d	compliant
FL24 EFG	Motorcycle	Bristol	M. Price	Urban multidrop	2.7 PSI	4d	attention
FL25 FGH	Van	Manchester	K. Ito	Trunking	3.1 PSI	5d	compliant
FL26 GHI	EV van	Preston	J. Bennett	Regional	3.5 PSI	6d	compliant
FL27 HIJ	Car	Leeds	S. Okafor	Depot shuttle	1.1 PSI	7d	compliant
FL28 IJK	EV car	Birmingham	R. Ahmed	Urban multidrop	1.5 PSI	8d	attention
FL20 JKL	Motorcycle	Bristol	L. Novak	Trunking	1.9 PSI	9d	critical
FL21 KLM	Van	Manchester	M. Price	Regional	2.3 PSI	10d	compliant
FL22 LMN	EV van	Preston	K. Ito	Depot shuttle	2.7 PSI	11d	compliant
FL23 MNO	Car	Leeds	J. Bennett	Urban multidrop	3.1 PSI	12d	attention
FL24 NOP	EV car	Birmingham	S. Okafor	Trunking	3.5 PSI	13d	compliant
FL25 OPQ	Motorcycle	Bristol	R. Ahmed	Regional	1.1 PSI	14d	compliant
FL26 PQR	Van	Manchester	L. Novak	Depot shuttle	1.5 PSI	15d · overdue	compliant
FL27 QRS	EV van	Preston	M. Price	Urban multidrop	1.9 PSI	16d · overdue	attention
FL28 RST	Car	Leeds	K. Ito	Trunking	2.3 PSI	17d · overdue	compliant
FL20 STC	EV car	Birmingham	J. Bennett	Regional	2.7 PSI	18d · overdue	critical
FL21 TUD	Motorcycle	Bristol	S. Okafor	Depot shuttle	3.1 PSI	19d · overdue	compliant
FL22 UBE	Van	Manchester	R. Ahmed	Urban multidrop	3.5 PSI	20d · overdue	attention
FL23 VCF	EV van	Preston	L. Novak	Trunking	1.1 PSI	0d	compliant
FL24 WDG	Car	Leeds	M. Price	Regional	1.5 PSI	1d	compliant
FL25 XEH	EV car	Birmingham	K. Ito	Depot shuttle	1.9 PSI	2d	compliant

Evidence base

What the compliance and economics numbers rest on

Fleet value is the same physics applied to higher mileage: tread life, energy, downtime and duty of care.

Tread life scales with utilisation

Abrasion tracks the energy dissipated in the contact patch, so a fleet running high mileage on soft tyres pays the wear penalty faster than a private car.^2008,1992

Energy is a line item

A 10% rolling-resistance change is worth roughly 1-2% of fuel, and inflation is the cheapest way to move it.^2006,2017

Structural failure risk is operational risk

Sustained under-inflation drives casing fatigue and roadside failure, and crash data links large pressure errors to tyre-related crashes.^2006,2012

Records are the compliance artefact

A dated, per-tyre record against an approved specification is what turns a maintenance intention into evidence.^2025,2026

Cited on this page

Grosch, K. A. (2008). Rubber Abrasion and Tire Wear. Rubber Chemistry and Technology, 81(3), 470-505.
Transportation Research Board, National Research Council (2006). Tires and Passenger Vehicle Fuel Economy (Special Report 286). National Academies Press.
US National Highway Traffic Safety Administration (2012). Tire-Related Factors in the Pre-Crash Phase (DOT HS 811 617). NHTSA National Center for Statistics and Analysis.
TyreSafe (2026). Stagnant road safety, surging tyre defects: analysis of the latest DfT casualty and collision figures. TyreSafe.

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

Fleet-wide edge and federated-learning position

These figures are read from the same persisted edge-compute session used on the simulator page. Change the tier, connectivity or power state there and this view follows.

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

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.
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.
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.
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.
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.
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.
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.
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

Compliance as a by-product

Every session writes an auditable record for the vehicle.

/Compliance/Exceptions/Duty cycles/Cost per mile/Downtime avoided/Audit trail/Compliance/Exceptions/Duty cycles/Cost per mile/Downtime avoided/Audit trail

Fleet economics

Tyres are a controllable line, not a fixed cost

Fleets already know their tyre spend. What they cannot see is which vehicles ran under-inflated, for how long, and what that did to replacement intervals - because nobody records a check that nobody performed.

Vehicles under management

Compliance rate

0.0%

Open exceptions

Repeat deviation, probable slow punctures, missed checks.

Modelled tread life gain

From removing sustained under-inflation across the fleet.

Every session is an evidenced check with a timestamp, a location, a before value and an after value. That converts a policy statement into an audit trail suitable for an operator licence or an insurer conversation.

Per-vehicle check history with pass, correct or exception status
Automatic escalation when a vehicle deviates repeatedly
Driver-level and depot-level views without exposing personal data
Exportable records for compliance and insurance review

Questions

Straight answers

No. The measurement happens at the machine, so a mixed-age fleet is covered from day one without retrofitting anything.

Session records are designed to be pushed into an existing telematics or fleet management platform through the documented API rather than replacing it.