Speakers: Marco Tezzele, University of Texas at Austin

Hosted at: SISSA, International School of Advanced Studies, Trieste, Italy, room 134.

Abstract:

In this talk, I will present two digital twin (DT) applications involving the structural health monitoring of a bridge and an unmanned aerial vehicle (UAV).
A DT is a virtualization of a physical asset built upon a set of computational models that dynamically update to persistently mirror a unique asset of interest throughout its operational lifespan, enabling informed decisions that realize value.
The first part of the talk is devoted to the health monitoring, predictive maintenance, and management planning of civil structures. The asset-twin coupled dynamical system is encoded using a probabilistic graphical model (PGM) which provides a general framework for data assimilation, state estimation, prediction, planning, and learning while accounting for the associated uncertainty. The assimilation of high-dimensional multivariate time series describing the vibration response is carried out by exploiting physics-based reduced order methods and deep learning models. The numerical models allow automated selection and extraction of optimized damage-sensitive features and real-time assessment of the structural state of a bridge.
In the second part of the talk, I will present a method to increase the personalization and robustness of DTs by using a PGM formulation, parametric Markov decision processes with transition probabilities modeled as random variables, and risk measures to account for rare and possibly fatal scenarios during a UAV mission. The impact is twofold: we increase the safety of DT deployments while we optimize operations resulting in lower operational costs and better predictive maintenance.