A probabilistic graphical model foundation for enabling predictive digital twins at scale

Kapteyn, Michael G.; Pretorius, Jacob V. R.; Willcox, Karen E.

doi:10.1038/s43588-021-00069-0

A probabilistic graphical model foundation for enabling predictive digital twins at scale

Journal Article · Thu May 20 00:00:00 EDT 2021 · Nature Computational Science

DOI:https://doi.org/10.1038/s43588-021-00069-0· OSTI ID:1784015

^[1]; Pretorius, Jacob V. R. ^[2]; ^[3]

Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States); Oden Institute for Computational Engineering and Sciences
The Jessara Group, Austin, TX (United States)
Univ. of Texas, Austin, TX (United States)

A unifying mathematical formulation is needed to move from one-off digital twins built through custom implementations to robust digital twin implementations at scale. This work proposes 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 formal definition of this coupled system as a probabilistic graphical model enables us to draw upon well-established theory and methods from Bayesian statistics, dynamical systems and control theory. The declarative and general nature of the proposed digital twin model make it rigorous yet flexible, enabling its application at scale in a diverse range of application areas. Here, we demonstrate how the model is instantiated to enable a structural digital twin of an unmanned aerial vehicle (UAV). The digital twin is calibrated using experimental data from a physical UAV asset. Its use in dynamic decision-making is then illustrated in a synthetic example where the UAV undergoes an in-flight damage event and the digital twin is dynamically updated using sensor data. The graphical model foundation ensures that the digital twin calibration and updating process is principled, unified and able to scale to an entire fleet of digital twins.

View Accepted Manuscript (DOE)

Research Organization:: Univ. of Texas, Austin, TX (United States)

Sponsoring Organization:: AFOSR; USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

Grant/Contract Number:: SC0019303; SC0021239

OSTI ID:: 1784015

Alternate ID(s):: OSTI ID: 1784022

Journal Information:: Nature Computational Science, Journal Name: Nature Computational Science Journal Issue: 5 Vol. 1; ISSN 2662-8457

Publisher:: Springer NatureCopyright Statement

Country of Publication:: United States

Language:: English

References (16)

Data‐driven physics‐based digital twins via a library of component‐based reduced‐order models Kapteyn, M. G.; Knezevic, D. J.; Huynh, D. B. P. International Journal for Numerical Methods in Engineering https://doi.org/10.1002/nme.6423	journal	June 2020
Model Order Reduction a Key Technology for Digital Twins Hartmann, Dirk; Herz, Matthias; Wever, Utz Reduced-Order Modeling (ROM) for Simulation and Optimization https://doi.org/10.1007/978-3-319-75319-5_8	book	January 2018
A survey of point-based POMDP solvers Shani, Guy; Pineau, Joelle; Kaplow, Robert Autonomous Agents and Multi-Agent Systems, Vol. 27, Issue 1 https://doi.org/10.1007/s10458-012-9200-2	journal	June 2012
A Bayesian state-space approach for damage detection and classification Dzunic, Zoran; Chen, Justin G.; Mobahi, Hossein Mechanical Systems and Signal Processing, Vol. 96 https://doi.org/10.1016/j.ymssp.2017.03.043	journal	November 2017
Data-Driven Science and Engineering Brunton, Steven L.; Kutz, J. Nathan https://doi.org/10.1017/9781108380690	book	February 2019
Towards AI-powered personalization in MOOC learning Yu, Han; Miao, Chunyan; Leung, Cyril npj Science of Learning, Vol. 2, Issue 1 https://doi.org/10.1038/s41539-017-0016-3	journal	December 2017
Learning about physical parameters: the importance of model discrepancy Brynjarsdóttir, Jenný; OʼHagan, Anthony Inverse Problems, Vol. 30, Issue 11 https://doi.org/10.1088/0266-5611/30/11/114007	journal	October 2014
Digital Twin: Values, Challenges and Enablers From a Modeling Perspective Rasheed, Adil; San, Omer; Kvamsdal, Trond IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.2970143	journal	January 2020
Human Digital Twin for Fitness Management Barricelli, Barbara Rita; Casiraghi, Elena; Gliozzo, Jessica IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.2971576	journal	January 2020
Smart city digital twins Mohammadi, Neda; Taylor, John E. 2017 IEEE Symposium Series on Computational Intelligence (SSCI) https://doi.org/10.1109/SSCI.2017.8285439	conference	November 2017
Reengineering Aircraft Structural Life Prediction Using a Digital Twin Tuegel, Eric J.; Ingraffea, Anthony R.; Eason, Thomas G. International Journal of Aerospace Engineering, Vol. 2011 https://doi.org/10.1155/2011/154798	journal	January 2011
Dynamic Bayesian Network for Aircraft Wing Health Monitoring Digital Twin Li, Chenzhao; Mahadevan, Sankaran; Ling, You AIAA Journal, Vol. 55, Issue 3 https://doi.org/10.2514/1.J055201	journal	March 2017
Integrated simulation model for preliminary aerodynamic, structural, and control-law design of aircraft Drela, Mark 40th Structures, Structural Dynamics, and Materials Conference and Exhibit https://doi.org/10.2514/6.1999-1394	conference	February 2013
The Digital Twin Paradigm for Future NASA and U.S. Air Force Vehicles Glaessgen, Edward; Stargel, David 53rd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference 20th AIAA/ASME/AHS Adaptive Structures Conference 14th AIAA https://doi.org/10.2514/6.2012-1818	conference	June 2012
Digital Twins in Health Care: Ethical Implications of an Emerging Engineering Paradigm Bruynseels, Koen; Santoni de Sio, Filippo; van den Hoven, Jeroen Frontiers in Genetics, Vol. 9 https://doi.org/10.3389/fgene.2018.00031	journal	February 2018
Digital Twin for Operations - Present Applications and Future Digital Thread Podskarbi, Mat; Knezevic, David J. Offshore Technology Conference, Day 3 Wed, May 06, 2020 https://doi.org/10.4043/30553-MS	conference	May 2020

Similar Records

Design of Digital Twin Sensing Strategies Via Predictive Modeling and Interpretable Machine Learning

Journal Article · Thu Aug 04 20:00:00 EDT 2022 · Journal of Mechanical Design · OSTI ID:1903120

Graphical Model Theory for Wireless Sensor Networks

Technical Report · Sat Dec 07 23:00:00 EST 2002 · OSTI ID:833692

Related Subjects

42 ENGINEERING
97 MATHEMATICS AND COMPUTING
Aerospace engineering
Computational science
Digital Twin
Digital twin
Probabilistic Graphical Model
Probabilistic graphical model
Self-aware vehicle
Uncertainty Quantification
Uncertainty quantification

A probabilistic graphical model foundation for enabling predictive digital twins at scale

Citation Formats

References (16)

Similar Records

Related Subjects