Factory Ecosystem Monitoring (FEM)

Challenge: Reduce infrastructure and through-life operational costs via real-time, agile monitoring of critical production environments.

Result: Estimated 5-10% improved machine utilisation, reduction in energy use (10-15%) and maintenance time (20%), arising from performance optimisation and enhanced resource utilisation.

What are we doing?

This industrial application use case will use sensor data and 5G to capture, monitor and gain insight of the changing variable conditions within a factory environment. Ultimately, this data will benefit operations by adjusting activities and settings to compensate for any changes in the environment. It will also provide insight into how the environment can affect operations and cause fluctuations in tolerances.

The sensors will provide feedback on internal factory and external local environmental conditions such as temperature, air pressure and humidity as well as external influences such as tides and lunar cycles, location data, building management systems supplying events data on electricity distribution, alarms and other events. They will also provide feedback on other events and influences such as machine movement, radio frequency identification scans, connections to human-machine interface on machines, shocks or exposure to extremes.

To understand the impact of 5G, all data will flow through the 5G network to realise the effects, impact, benefits, and constraints of 5G on the manufacturing processes.

Why are we doing it?

This use case seeks to explore solutions to a number of challenges:

  1. The ability to monitor the environment around manufacturing facilities that could influence operations, quality, productivity, and efficiencies. This includes internal and external variables; 
  2. To learn ‘what’ influences affect processes; 
  3. To understand and compensate for the above influences; 
  4. To create a flexible manufacturing capability with minimal fixed infrastructure where the effects of the environment in different locations can be captured, understood, and controlled to allow flexibility and agility. 
  5. To monitor the health of machines in real-time. 
  6. To prove that machines can ‘return to home’ positions based on events such as fire alarms.
  7. To prove visual recognition performance on a 5G network to identify parts and orientations using the automatic kitting cell.