The DigitalTwin from an Artificial Intelligence Perspective
This addresses the problem of reducing modeling efforts and synchronizing results for developers and users of AI services in Cyber-Physical Systems, but it appears incremental as it builds on existing DigitalTwin concepts.
The paper tackles the need for a unified virtual representation in AI-driven Cyber-Physical Systems by defining the AITwin reference model, which is verified through a process industry example and analysis of recent projects.
Services for Cyber-Physical Systems based on Artificial Intelligence and Machine Learning require a virtual representation of the physical. To reduce modeling efforts and to synchronize results, for each system, a common and unique virtual representation used by all services during the whole system life-cycle is needed, i.e. a DigitalTwin. In this paper such a DigitalTwin, namely the AI reference model AITwin, is defined. This reference model is verified by using a running example from process industry and by analyzing the work done in recent projects.