Research
|
Projects
Constellations

Data for Efficient Meat Processing

Combining digital twins, generative AI and workforce expertise to identify and resolve production issues across food manufacturing operations in real time.
Project complete

In Partnership With:

Kilcoy Global Foods
Royal Melbourne Institute of Technology

Data for Efficient Meat Processing

“The real value is how the AI talks directly with our teams, in plain language they use every day and guides them straight to the fix. That's what turns a clever detection system into faster resolutions and fewer repeat problems."

- Jiah Falcke, President at Kilcoy Global Foods

The Challenge

Kilcoy Global Foods (KGF) primary processing site in Kilcoy, Queensland, is one of the largest grain-fed beef processing facilities in Australia.

The site is operational 24/7 which means identifying potential issues and anomalies usually only happens after production or once the issue has become critical.

These major issues and anomalies can have a material impact on business efficiency and overall yield.

The Solution

The project team will create digital twins with generative AI agents that have genuine operational understanding. The agents can combine ontology, knowledge graph and retrieval-augmented generation techniques so that raw data signals arrive with the full context of the process, product and plant behind it.

This ensures the AI agents can make informed decisions and alert team members as required. The layered technology provides early warning signs for anomalies, meaning potential issues can be addressed before they become critical.

However, detecting a problem is only half the challenge, and in a heavily instrumented plant, detecting everything can create a new problem entirely: alert fatigue.

The pilot's defining innovation is the judgement applied at this point. A generative AI agent captures and triages every detected issue, then decides what genuinely needs human oversight.

This allows messages to reach the floor team directly through the communication tools they use every day, and parks messages that can be raised with management the next day. The result is that when the AI does interrupt someone, it matters, and the team's trust in the system grows with every alert.

Outcomes

  • Creation of a generative AI agent with genuine understanding of KGF operations
  • Improved efficiency and yield
  • Technology to empower staff decision making

Project Updates

August 2026 - News: AI-powered manufacturing pilot delivers early win

meet the team

No items found.

publications

No items found.

other projects

related projects

No items found.