Digital Twin-Enabled Decision Support Services in Industrial Ecosystems

Abstract

The goal of this paper is to further elaborate a new concept for value creation by decision support services in industrial service ecosystems using digital twins and to apply it to an extended case study. The aim of the original model was to design and integrate an architecture of digital twins derived from business needs that leveraged the potential of the synergies in the ecosystem. The conceptual framework presented in this paper extends the semantic ontology model for integrating the digital twins. For the original model, technical modeling approaches were developed and integrated into an ecosystem perspective based on a modeling of the ecosystem and the actors’ decision jobs. In a service ecosystem comprising several enterprises and a multitude of actors, decision making is based on the interlinkage of the digital twins of the equipment and the processes, which is achieved by the semantic ontology model further elaborated in this paper. The implementation of the digital twin architecture is shown in the example of a manufacturing SME (small and medium-sized enterprise) case that was introduced in. The mixed semantic modeling and model-based systems engineering for this implementation is discussed in further detail in this paper. The findings of this detailed study provide a theoretical concept for implementing digital twins on the level of service ecosystems and integrating digital twins based on a unified ontology. This provides a practical blueprint to companies for developing digital twin based services in their own operations and beyond in their ecosystem.

On the Value of Data: Multi-Objective Maximization of Value Creation in Data-Driven Industrial Services

“…Also business processes create data, typically in the form of time stamps from work flow tools, that can be shared with the service provider and combined with the data from the equipment, for enabling value-creating interventions. The provider can then create digital models representing the customer's products, processes, and operations (e.g., digital twins [12]). These models describe past, current or predicted future states of of the equipment and processes and thus may provide decision advisory for management actions.…”

Exploring the concept of Cognitive Digital Twin from model-based systems engineering perspective

“…For example, the IOF-MBSE domain ontology is used in [23] to describe co-simulation models based on a standardized artifact representation. Then, using the same ontology, semantic models are used to represent the model structure of verification models in order to realize DT integration [24]. However, the manual construction of ontologies is a time-consuming task [25] which restricts the applications of semantic models.…”

Exploring the Concept of Cognitive Digital Twins from Model-Based Systems Engineering Perspective

“…For example, the IOF-MBSE domain ontology is used in [21] to describe co-simulation models based on a standardized artifact representation. Then, using the same ontology, semantic models are used to represent the model structure of verification models in order to realize digital twin integration [22]. However, the manual construction of ontologies is a time-consuming task [23] which restricts the applications of semantic models.…”