Life Cycle Assessment through Energy Monitoring
General Information
Challenge, Value & Description
Performance, Access & Contact
1 – General Information
Partners
Sectors addressed
Application categories covered
Lifecycle level covered
Digital Engineering
Planning & Commissioning
Smart Production & Operations
Smart Maintenance
Customer Service
Circularity
3 Viale Aeronautica, Pomigliano D'arco, NA 80038, Italia
Geographical Scope
- Europe
- Southern Europe (Italy, Spain, Portugal, Greece)
2 – Challenge, Value & Description
Challenge
Robotic arms are subjected to eventual failures and faults; such faults, when they happen unpredicted, cause the production to halt until maintenance can be scheduled, depending also on what component faulted and the lead time on that component refurbishment. Machines are kept working until their broken point is reached.
The pilot aims to extend the robotic arm’s life cycle, reduce unplanned downtime, and enable predictive maintenance. By monitoring and analyzing the current absorbed during robot movement, valuable data can be collected to optimize both performance and maintenance scheduling. This not only improves operational efficiency but also supports sustainability goals through energy monitoring, while efficient maintenance practices generate cost savings and reduce waste for the company.
Value
After the implementation of the use case, customers benefit from a secure cloud-based data space where production information is shared seamlessly across plants worldwide. Leveraging COMAU In.Grid Robot monitoring tool, maintenance teams can act proactively, preventing failures and reducing unplanned downtime. This results in lower maintenance costs, higher equipment availability, and improved decision-making based on real-time data. Moreover, Comau’s after-sales services are enhanced with predictive maintenance support, offering added value to customers through increased reliability and reduced operational disruptions.
By employing predictive maintenance techniques, it’s possible to prepare spare parts beforehand and limit the duration of downtimes. Also, by avoiding wearing a machine to the limit the number of critical faults may decrease as well. By leveraging the dataspace as a means to exchange data and utilise service providers, COMAU will have an AI-as-a-Service solution capable of predicting robotic arm consumption and failures, providing a powerful basis for operations and maintenance planning.
Description
Data generated by installed machine is being collected, though dedicated devices, and deposited in In.Grid,
the fleet management solution of COMAU. In.Grid will publish the data on the DataSpace in order to share it
with the AI service and collect back the produced forecast.
During production, data is continuously gathered, temporarily buffered, and securely sent to the In.Grid Digital Platform and then to the Data Space. At defined intervals or upon specific events, advanced algorithms—including AI models—process the information to deliver actionable insights. These insights are then shared with the customer and the robot manufacturer’s after-sales department, supporting proactive maintenance, performance optimization, and more informed decision-making.
Data Value Chain Description
Infraestructure Elements
- Sovereign Cloud
- Private Cloud
- HPC
3 – Performance, Access & Contact Info
Performance
The AI solution is being tested and improved, to both forecast consumption trends and predict future occurring anomalies; data can be shared through a demo dataspace, which is being worked on to identify the supporting infrastructure and the best deployment solution.