Method ensures accurate identification of delayed system dynamics
Identifiability Guarantees for Drivers and Dynamics of Delayed Physical Systems
Machine Learning
Summary
Understanding how physical systems with delays behave is hard, especially when randomness is involved. Many existing methods can't always tell what drives these systems or how they change over time. The authors developed a new method that can reliably identify both the causes and changes in such delayed systems, and they proved this works under reasonable conditions. Their approach performed better than others on tests measuring how well such drivers and dynamics can be identified.
What this means in practice
- •For control system engineers: Identify driving forces and dynamic changes in delayed physical systems to improve system control and prediction.
- •For robotics development teams: Detect and model delayed interactions affecting robot behavior to enhance precision and reliability in robotic systems.
Authors
Julien Boussard, Antoine Débouchage, Théo Saulus
Abstract
A wide range of methods have been proposed, including physics-informed neural networks, which are powerful but do not guarantee identifiability of the dynamics, symbolic regression, which requires a set of precomputed operations, and causal discovery, which is more principled but usually relies on strong assumptions that physical systems may violate. In this work, we develop a theory-grounded method and prove that under a set of permissive assumptions, the structural drivers and drift of stochastic delayed differential equations are identifiable. Our method outperforms others on a benchmark for driver identifiability, and on a second benchmark to evaluate physical consistency of the learned dynamics.