Probabilistic Digital Twins for Diagnosis, Prognosis and Decision-Making
Research at Vanderbilt University
The digital twin paradigm integrates information obtained from sensor data, physics models, as well as operational and inspection/maintenance/repair history of a physical system or component of interest. As more and more data becomes available, the resulting updated model becomes increasingly accurate in predicting future behavior of the system, and can potentially be used to support several objectives, such as sustainment, mission planning, and operational maneuvers. In recent years, advances have been made in digital twin methodologies to support all three objectives, based on several types of computation: current state diagnosis, model updating, future state prognosis, and decision-making.
One important issue is that these computations are affected by uncertainty regarding system properties, operational parameters, usage and environment, as well as uncertainties in data and the prediction models. Therefore, researchers at Vanderbilt University (Risk, Reliability and Resilience Engineering group) are addressing uncertainty quantification in diagnosis and prognosis (considering both aleatory and epistemic uncertainty sources), and decision-making under uncertainty. Scaling up the probabilistic digital twin methodology to support real-time decision-making under uncertainty is another challenge that is being addressed, and several strategies that combine recent advances in sensing, computing, data fusion and machine learning have been developed to enable the scale-up.
The developed probabilistic digital twin techniques have been demonstrated for use cases related to aircraft, rotorcraft, marine vessels, and additive manufacturing. The decisions are related to sustainment (inspection scheduling, predictive maintenance), mission planning, operational maneuvers during a mission, and manufacturing process quality control. The research has been funded by U. S. Air Force, U. S. Army, NASA, NIST, and ABS.