Skip to content
This is NOT an official site of the Government of Canada. Click here for the official AI registry.

Helpful Places

Government of Canada – DTPR AI Register

Back to your search

AI-Assisted Fault Detection for Industrial Processes and Buildings

Energy Efficiency · Planning & Decision-making

What it collects

About a measurement
Anonymized data
  • Sensor and process readings from industrial equipment and building systems — such as temperature, pressure, flow rates, and energy consumption metrics — sourced from public and private databases.
Operational data
Anonymized data
  • Operational records from process industry facilities and buildings, drawn from both public and private data sources, used to build machine learning performance models.
Run by
Natural Resources Canada (NRCan)
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

Energy EfficiencyPlanning & Decision-making

This tool uses machine learning and causality analysis to automatically detect and diagnose energy inefficiencies, quality problems, and equipment malfunctions in industrial processes and buildings. It connects to databases, prepares data, and builds performance models without manual intervention. The system is used by both government employees and the public. Importantly, users are not currently informed that AI is being used.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Sensor and process readings from industrial equipment and building systems — such as temperature, pressure, flow rates, and energy consumption metrics — sourced from public and private databases.
Operational data
Anonymized data
  • Operational records from process industry facilities and buildings, drawn from both public and private data sources, used to build machine learning performance models.

Processing

Classification & Prediction
  • Machine learning ensemble models classify fault conditions and predict energy inefficiencies or equipment malfunctions based on historical and live process data.
Anomaly Detection
  • The causality analysis component identifies unusual patterns and deviations from normal process behaviour to flag potential faults for diagnosis.

What it does

Deciding (Analytical AI)
Human decides
  • An ensemble of machine learning algorithms classifies and scores process data to detect faults and diagnose their causes. The system outputs findings for human review and response.
Sensing (Perceptive AI)
Human decides
  • The tool connects to databases online and prepares raw process data automatically, transforming it into structured inputs for the machine learning models.

Outputs

A recommendation or prediction
Anonymized data
  • The system produces fault diagnoses and identifies root causes of energy inefficiencies, quality issues, and equipment malfunctions — advisory outputs for engineers or facility managers to act on.
Operational data
Anonymized data
  • Machine learning performance models built by the tool can be retained for ongoing monitoring and future diagnosis of process or building systems.

Run by

Natural Resources Canada (NRCan)
  • Natural Resources Canada is the federal department responsible for deploying this automated fault diagnosis tool. It is also credited as the developer of the system.

Government of Canada AI Register — 2526-NRCan-RNCan-004

Built by

Government of Canada
  • The Government of Canada developed this system in-house. There is no separate private vendor; development and deployment are both conducted within government.

Government of Canada AI Register — 2526-NRCan-RNCan-004

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization
  • Diagnostic outputs and performance models are available to Natural Resources Canada and the employees and public users who operate or interact with the system.
Not available to me
  • The register indicates that AI use is not disclosed to users (AI use disclosed to users: N), meaning individuals subject to the system's outputs are not informed of or given direct access to the AI-generated diagnoses.

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 Be Informed of AI UseUsers and affected parties have the right to be informed that this tool uses AI to diagnose process faults. However, the official register records that AI use is currently not disclosed to users. Individuals who believe they are affected may contact Natural Resources Canada for information.
  • Right to Algorithmic TransparencyUsers have the right to understand in plain terms how the machine learning ensemble and causality analysis approach work and what types of faults they are designed to detect. Contact Natural Resources Canada for further information about the system's logic and methodology.

Risks and safeguards

  • Civil liberties harmThe system does not disclose its AI use to users (AI use disclosed to users: N), raising transparency and notice concerns. Individuals and organisations whose process or building data is analysed may not know AI is involved. No specific mitigation measures are described in the register. Recommended mitigations include clearly disclosing AI involvement to affected users and providing a mechanism to understand and challenge AI-generated diagnoses.