Towards the Augmentation of Digital Twin Performance

Area of Science:

• Industrial Engineering
• Computer Science
• Cyber-Physical Systems

Background:

• Digital Twin (DT) technology offers visualization, analysis, and simulation for industrial production.
• Existing DT methodologies face challenges in data contextualization for effective process supervision.
• Cyber-Physical Systems (CPS) generate performance data crucial for industrial monitoring.

Purpose of the Study:

• To extend Digital Twin capabilities for enhanced process supervision.
• To introduce a novel framework for data identification, collection, and analysis within DT.
• To integrate Key Performance Indicators (KPIs) for real-time monitoring.

Main Methods:

• Literature review of existing Digital Twin methodologies and data contextualization.
• Development of a framework to identify, collect, and analyze performance data from production systems.
• Implementation of Key Performance Indicators (KPIs) within an immersive DT environment for case study monitoring.

Main Results:

• A novel framework was developed and implemented to enhance DT functionalities for process supervision.
• Key Performance Indicators (KPIs) were successfully integrated into the DT's immersive environment.
• The methodology enables monitoring of physical processes through their cyber representations, improving performance insights.

Conclusions:

• The proposed methodology extends DTs for effective process supervision by integrating data analysis and KPIs.
• The framework facilitates the monitoring of machine and production line performance via DTs.
• This approach addresses industrial challenges and opens possibilities for applications like predictive maintenance.