(+55) 254. 254. 254
Helios Tower 75 Tam Trinh Hoang Mai - Ha Noi - Viet Nam
$250 000+ energy & water abnomal usage detected in 2020
New Zealand leader – High-quality meat
The food factory produces high-value food products with seasonal demand.
The factory’s production doubles between the winter and the summer season.
This changing environment creates major internal adaptation to maintain a high-performing factory with the lowest possible costs all year round.
Therefore the energy and water demand is unstable and hardly accurately predictable.
Demand-based shift schedule
The demand is constantly changing in this factory.
Therefore shifts schedules can change overnight.
It is usually a business decision taken a few days prior to the change.
The machine needs to adapt quickly to follow business decisions and maintain a high level of accuracy and reliability.
These shift changes reflect the reality of the market. It is key to manage and predict energy and power usage.
It’s never been easier for factories to monitor their equipment and operations, but the ease of deploying thousands of sensors results in a challenging volume of sensor data.
The factory uses IoT devices and meter to track energy and water usage.
The monitoring team has a limited capacity to constantly monitor the entire factory.
1. Detect and predict regular usages with AI
AI takes into account any event that happens at the factory:
- New equipment load commissioned
- Weather impact (HDD/CDD)
- Production and demand change
2. Shift change detection
Using usage data AI is able to detect shift changes without any manual inputs.
The AI system will seamlessly detect this change and adjust the analysis.
When the leadership team changes the shift schedule, the AI system picks up the change and detect on shift/off shift energy and water waste.
3. Duty cycles detection
The factory uses duty cycles for some of their equipment loads such as air compressors.
Meaning that air compressors work alternatively.
The solution is able to detect automatically duty cycles and detect drifts by combining their usage data.