Adaptive digital twin for multi-variety production: a knowledge model-driven modeling approach with process information digital model interaction support

The production requirements of multi-variety and high-quality products pose significant challenges for implementing intelligent production lines that integrate process sensing, adaptive processing, and precise decision-making. Digital twin is the key enabling technology for intelligent production lines, but it lacks the perception of multidimensional process information to enable adaptive production. Thus, this paper proposes the adaptive digital twin motivated by a knowledge model with process information interactions. First, the process information related to product quality is located, and the process information is digitally modeled to implement the virtual-real mapping. Second, multidimensional feature extraction and fusion of process information digital model are performed to form adaptive adjustment capabilities for multi-variety production. Finally, the formal modeling of the adaptive adjustment capability enables the construction of the knowledge model that drives the adaptive digital twin. In adaptive digital twin, the virtual and real mapping of process information facilitates the knowledge model to continuously update the domain knowledge, which enables the adaptive decision-making ability to dynamically adapt to different processing requirements in the physical model. As a fusion technique developed in intelligent production lines, the modeling of adaptive digital twin has been well applied and validated in commutator finishing lines.