AI-Powered Predictive Maintenance for Airport Screening Equipment

Safety & Security

What it collects

About a measurement

Anonymized data

Sensor readings and operational telemetry from airport screening equipment — such as usage cycles, vibration, temperature, error counts, and performance metrics — used to train and run the predictive models. This data describes machine behaviour, not individuals.

Operational data

Anonymized data

Maintenance logs, equipment schedules, historical failure records, and service history associated with screening machines at Canadian airports. Used alongside sensor data to build predictive models.

Run by: Canadian Air Transport Security Authority (CATSA)
Where: No fixed location
Kept: Not stated by the Helpful Places.
Shared with: Accountable organization
Your copy: You cannot see the data it holds about you. What you can do

What it is for

Safety & Security

This system uses artificial intelligence to predict when airport security screening equipment is likely to fail, allowing maintenance teams to act before a breakdown occurs. It is operated by the Canadian Air Transport Security Authority and is currently in development. The system primarily affects equipment availability rather than individual travellers, and its outputs are used internally by maintenance staff.

What it collects and what happens to it

Data taken in

About a measurement

Anonymized data

Sensor readings and operational telemetry from airport screening equipment — such as usage cycles, vibration, temperature, error counts, and performance metrics — used to train and run the predictive models. This data describes machine behaviour, not individuals.

Operational data

Anonymized data

Maintenance logs, equipment schedules, historical failure records, and service history associated with screening machines at Canadian airports. Used alongside sensor data to build predictive models.

Processing

Classification & Prediction

Machine learning models predict the probability and timing of equipment failures for individual screening machines, producing failure-risk scores or time-to-failure estimates that maintenance teams use to prioritize interventions.

What it does

Deciding (Analytical AI)

Human decides

The system predicts the likelihood of equipment failure using operational data from screening machines. Maintenance staff review these predictions and decide when and how to act — the AI is advisory, and humans remain in the loop on every maintenance decision.

Outputs

A recommendation or prediction

Anonymized data

Failure-risk scores, predicted time-to-failure estimates, and maintenance priority recommendations for specific screening machines. These outputs advise maintenance staff but do not autonomously trigger any maintenance action.

Run by

Canadian Air Transport Security Authority (CATSA)

CATSA is the federal Crown corporation responsible for screening passengers and their belongings at designated Canadian airports. It is deploying this predictive maintenance system to optimize the availability of its screening equipment.

Government of Canada AI Register — 2526-CATSA-ACSTA-012

Built by

Not stated by the Helpful Places.

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization

Predictive outputs and maintenance recommendations are available internally to CATSA maintenance and operations staff. The register does not indicate access by external parties or the public.

Not available to me

Outputs of this system relate to equipment performance rather than individuals. There is no individual access mechanism because no personal data about travellers or the public is produced or stored.

Stored

Not stated by the Helpful Places.

How to read the colours

Can it identify you?

Anonymized data: Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data: Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data: The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides: This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes: This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous: This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the Helpful Places, not the vendor.

Your rights

Right to Algorithmic TransparencyThis system has been disclosed on the Government of Canada's AI and Data Solutions Register, providing public transparency about its existence, purpose, and status. The system processes equipment data rather than personal data, so individual rights of access or explanation do not apply in the conventional sense.

Risks and safeguards

Financial & business harmIncorrect failure predictions could lead to unnecessary maintenance expenditures (false positives) or missed failures resulting in costly emergency repairs and service disruptions (false negatives).Safeguard: Human maintenance staff review all predictions before acting; the system is advisory and does not autonomously trigger work orders. Model performance should be monitored and refined over time as the system moves from development to production.