Session 4: Digital Twins: From Physics-Based Modeling to Scientific Machine Learning
A digital twin is an evolving virtual model that mirrors an individual physical asset throughout its lifecycle. Key to the digital twin concept is the ability to sense, collect, analyze, and learn from the asset's data. This talk will discuss the ways in which digital twins have the potential to transform design, manufacture, and operation of engineering systems. To make digital twins a reality, many elements of the interdisciplinary field of computational science, including physics-based modeling and simulation, inverse problems, uncertainty quantification, and scientific machine learning, have an important role to play. In this work, we develop a probabilistic graphical model as a formal mathematical representation of a digital twin and its associated physical asset. We create an abstraction of the asset-twin system as a set of coupled dynamical systems, evolving over time through their respective state-spaces and interacting via observed data and control inputs. The abstraction is realized computationally as a dynamic decision network. Predictive capabilities are enabled by physics-based reduced-order models.
We demonstrate how the approach is instantiated to create, update and deploy a structural digital twin of an unmanned aerial vehicle.
Key Takeaways
- A probabilistic graphical model provides a formal mathematical foundation for digital twins, on which we layer data assimilation, model updating, optimal control, and end-to-end uncertainty quantification.
- Predictive digital twins require a synergistic combination of physics-based modeling and data-driven learning.
- We demonstrate the definition, creation, updating and use of a structural digital twin for a custom-built unmanned aerial vehicle.
Register Today.
Speaker/Presenter: Karen E. Willcox
Director of the Oden Institute for Computational Engineering and SciencesUniversity of Texas at Austin
About Karen
Karen E. Willcox is Director of the Oden Institute for Computational Engineering and Sciences, Associate Vice President for Research, and Professor of Aerospace Engineering and Engineering Mechanics at the University of Texas at Austin. She is also External Professor at the Santa Fe Institute. Before joining the Oden Institute in 2018, she spent 17 years as a professor at the Massachusetts Institute of Technology, where she served as the founding Co-Director of the MIT Center for Computational Engineering and the Associate Head of the MIT Department of Aeronautics and Astronautics.
Prior to joining the MIT faculty, she worked at Boeing Phantom Works with the Blended-Wing-Body aircraft design group. She is a Fellow of the Society for Industrial and Applied Mathematics (SIAM) and Fellow of the American Institute of Aeronautics and Astronautics (AIAA).
Moderator: Kenneth Wong
Senior EditorDigital Engineering
About SimScale
SimScale enables engineering teams to access accurate and fast simulation, on their terms, without compromise. We make engineering simulation technically and economically accessible from everywhere, at any time, and at any scale, in the cloud. We deliver instant access to fluid, thermal, and structural simulation to hundreds of thousands of users worldwide. With SimScale, high-fidelity multiphysics simulation has moved from a complex and cost-prohibitive desktop application to an inclusive, agile, cloud-native engineering simulation platform. SimScale is a SaaS company that follows the subscription pricing model, visit simscale.com for more information. Simulate early. Simulate more. Simulate now, with SimScale.
177 Huntington Ave, Ste 1703
Boston, Massachusetts, 02115-3153
Boston, Massachusetts, 02115-3153
SimScale Resources
A boon to engineering design, multiphysics simulation is a longstanding process that has improved with technology to provide valuable design results.
Simulation brings many benefits to design engineering—but it’s not a one-size-fits-all option for certain use cases.
Companies make high-fidelity CFD available in the cloud.
Digital Twin News
Built with cloud-native technology, the updated platform offers enhanced performance and security while providing flexible deployment options—on-premise, air-gapped, cloud-based, or hybrid. Featuring a low code, no code toolset, CLOVER's self-service capabilities allow organizations to set up and maintain integrations independently without expensive technical resources or domain expertise.
Digital Twin Resources
Our Special Focus Issue on industrial manufacturing will take a look at new advances in digital twins, digital manufacturing, and PLM.
In this special digital issue, we examine how NVIDIA Omniverse and digital twin technology are advancing new engineering and design workflows.
In this Special Focus Issue of Digital Engineering, learn about new innovations in digital twin, digital thread and PLM technology.
View any track or session
Sign up to attend all sessions.
Reserve your space now and
we'll send you a reminder before the event.
we'll send you a reminder before the event.