An architecture of an Intelligent Digital Twin in a Cyber-Physical Production System
The article advocates that there’s no encompassing architecture covering necessary components of a Digital Twin to realize various use cases in an intelligent automation system.
The article discusses the added value an Intelligent DigitalTwin (a twin with AI) can provide in an intelligent automation system and the benefit of co-simulation frameworks such as the Anchor-Point-Method (heterogeneous data acquisition and data integration).
Why it’s relevant to Nextspace
This article is of interest to Nextspace Partners wanting to build a digital twin for the purpose of making systems easily reconfigurable and testing reconfiguration scenarios through simulation.
The article proposes an architecture incorporating:
- A unique identifier (GUID)
- Interfaces that provide interaction between models
- Version management
- Operations data
- Organization and technical data
- Relationships to other digital twins
- A co-simulation interface
- A synchronization interface
- A data-acquisition interface
An Intelligent Digital Twin requires additional components to deliver intelligence:
- Semantic connection, eg: OPC UA and OWL
- Algorithms – behavior models, optimization, code automation, correlations
- Semantic description of Services
- Feedback
The article goes on to discuss usage and challenges, synchronization over lifecycles, the Anchor-Point-Method to detect and analyse changed components integrating real world data, and co-simulation.
The article has an extensive list of references for further reading.
