An interactive framework to support decision-making for Digital Twin design

Abstract

Producing a Digital Twin (DT) involves many inter-linking decisions. Existing research tends to describe the parts of a DT and how they work, but not the decision-making that goes into building a DT nor the consideration of alternative design options. There is therefore a need for decision support to guide developers to create DTs efficiently while meeting functional requirements such as accuracy and interoperability. This paper presents an ontology-based decision support framework to achieve this need. Firstly an analysis of the decisions required to create a predictive maintenance DT for an automotive manufacturer is performed. The analysis found that each decision point produces an output by consideration of various influencing factors, such as time constraints, computation limits and the required fidelity of the model. The network of decisions is complex, with the outcomes of earlier decisions influencing later ones. An IDEF0 diagram was found to be a useful way to represent decisions, their dependencies and their cross-linking. This knowledge was used to populate an ontology of DT components for a predictive maintenance DT. The ability of an ontology to describe concepts explicitly using standardised vocabulary ensures the integrity of the decision-making guidance. A demonstration of the functionality of the ontology-based decision support framework was made before an evaluation of the concept. The research is a fundamental component in producing decision support for DT creators so that manufacturers can realise the benefits of a connected, responsive and flexible facility.