Adaptive planning for risk-aware predictive digital twins

TL;DR

This paper introduces a mathematical framework for creating risk-aware digital twins using probabilistic models, enabling adaptive decision-making to handle rare events and improve robustness in complex systems.

Contribution

It develops a novel approach combining probabilistic model-checking and linear programming within dynamic Bayesian networks to construct adaptive, risk-averse digital twins.

Findings

Enhanced robustness to rare events in digital twins.

Effective adaptive policy refinement at each time step.

Successful application to UAV digital twin with mission replanning.

Abstract

This work proposes a mathematical framework to increase the robustness to rare events of digital twins modelled with graphical models. We incorporate probabilistic model-checking and linear programming into a dynamic Bayesian network to enable the construction of risk-averse digital twins. By modeling with a random variable the probability of the asset to transition from one state to another, we define a parametric Markov decision process. By solving this Markov decision process, we compute a policy that defines state-dependent optimal actions to take. To account for rare events connected to failures we leverage risk measures associated with the distribution of the random variables describing the transition probabilities. We refine the optimal policy at every time step resulting in a better trade off between operational costs and performances. We showcase the capabilities of the proposed framework with a structural digital twin of an unmanned aerial vehicle and its adaptive mission replanning.