Abstract

Predictive digital twins of cyber-physical systems can be very useful for evaluating and choosing among decision alternatives that arise during development, operations, and maintenance of these systems; applications include model-based engineering, model-based decision support for human decision-makers, and automated decision-making for autonomous systems. In the context of development, the digital twin would typically be based on the current intended design for the given system. In the case of operations and maintenance, however, it is crucial to ensure that the digital twin represents the precise current state of the system, accurately reflecting any and all changes that have occurred over the system’s lifetime, from wear and tear on hardware components, to updates to software components, and any other modifications that may have occurred, e.g. components that have been added or removed, connections that have been made or broken, and any new software that may have been uploaded. One way to accomplish this is to create the digital twin at the same time we create the actual system, and then, every time any change occurs to the real system, we would make the corresponding change to the digital twin. However, this kind of “parallel maintenance” strategy is inefficient, error-prone, and burdensome. A much better approach, in our view, is to implement a facility that enables us to autogenerate an up-to-date digital twin on demand, whenever we need it. The design of such a facility is no small challenge, not when the objective is to make it work for any kind of cyber-physical system, no matter how complex, but it can be done. In this presentation we will describe an innovate component-based software technology for model-based engineering and DevOps of cyber-physical systems that provides just such a facility. An earlier version of this same technology was described in our presentation "Combining Heterogenous Models" at the 2017 NAFEMS conference on Multiscale and Multiphysics Modeling & Simulation - Innovation Enabling Technologies.