AI System for Reviewing Facility Water Consumption Variances

The problem

In day-to-day operations, a total meter reading can conceal a variance within a department. When water meter, department, production, shift, weather, cleaning and maintenance records are scattered across sensors, documents, field records or team files, issues may not become visible in time.

This fragmented data delays preparation of the water consumption review file and forces teams to search manually for supporting evidence again. The facilities or environmental engineer must complete missing records and verify each conflict before making a decision.

A common exception is that cleaning, filling or meter maintenance may cause a temporary increase. Incomplete or incorrect automation that fails to check this context could lead to an inappropriate valve intervention or delay the discovery of a genuine leak, so no physical or operational action can be carried out directly.

What we set out to improve

• Proportion of water variances verified by the engineer
• Proportion of outputs corrected or rejected by the facilities or environmental engineer
• Time between the source event and the review output

How the system works

1. 01 Define the review scope and the role of the authorised facilities or environmental engineer
2. 02 Retrieve the inputs: water meter, department, production, shift, weather, cleaning and maintenance records
3. 03 Check source identity, date, calibration or version, and data recency
4. 04 Check meter and department identities
5. 05 Compare consumption with the operational context
6. 06 Check for exceptions: cleaning, filling or meter maintenance may cause a temporary increase
7. 07 Place low-confidence or conflicting records in a separate specialist queue
8. 08 Write the source identity, rule, output and timestamp to the audit trail
9. 09 Have the facilities or environmental engineer approve, correct, defer or reject the output

Methods we used

• Time-series variance checks based on activity levels
• Source, format, timing and required-field checks for water meter, department, production, shift, weather, cleaning and maintenance records
• A missing-data warning instead of an estimate when inputs are incomplete or conflicting
• A separate exception check outside the main rule
• Combined retention of the source, rule result, water consumption review file and human decision

Where people stay involved

Data and security

Access to water meter, department, production, shift, weather, cleaning and maintenance records is restricted to the minimum permissions required for the task. Commercial, location and employee information is masked where possible, and only the necessary portion of the dataset is sent to the model. Access, outputs and the facilities or environmental engineer's decision are logged; production use does not begin until the organisation has approved the retention period and data location.

Who this suits

Frequently asked questions