An official website of the United States government
Identifying disturbances in network-coupled dynamical systems without knowledge of the disturbances or underlying dynamics is a problem with a wide range of applications. For example, one might want to know which nodes in the network are being disturbed and identify the type of disturbance. Here, we present a model-free method based on machine learning to identify such unknown disturbances based only on prior observations of the system when forced by a known training function. We find that this method is able to identify the locations and properties of many different types of unknown disturbances using a variety of known forcing functions. We illustrate our results with both linear and nonlinear disturbances using food web and neuronal activity models. Finally, we discuss how to scale our method to large networks.
more »
« less
Suppressing unknown disturbances to dynamical systems using machine learning
Abstract Identifying and suppressing unknown disturbances to dynamical systems is a problem with applications in many different fields. Here we present a model-free method to identify and suppress an unknown disturbance to an unknown system based only on previous observations of the system under the influence of a known forcing function. We find that, under very mild restrictions on the training function, our method is able to robustly identify and suppress a large class of unknown disturbances. We illustrate our scheme with the identification of both deterministic and stochastic unknown disturbances to an analog electric chaotic circuit and with numerical examples where a chaotic disturbance to various chaotic dynamical systems is identified and suppressed.
more »
« less
- Award ID(s):
- 2205967
- PAR ID:
- 10561258
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- Communications Physics
- Volume:
- 7
- Issue:
- 1
- ISSN:
- 2399-3650
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abate, Alessandro; Cannon, Mark; Margellos, Kostas; Papachristodoulou, Antonis (Ed.)In this paper, we introduce a data-driven framework for synthesis of provably-correct controllers for general nonlinear switched systems under complex specifications. The focus is on systems with unknown disturbances whose effects on the dynamics of the system is nonlinear. The specification is assumed to be given as linear temporal logic over finite traces (LTLf) formulas. Starting from observations of either the disturbance or the state of the system, we first learn an ambiguity set that contains the unknown distribution of the disturbances with a user-defined confidence. Next, we obtain a robust Markov decision process (RMDP) as a finite abstraction of the system. By composing the RMDP with the automaton obtained from the LTLf formula and performing optimal robust value iteration on the composed RMDP, we synthesize a strategy that yields a high probability that the uncertain system satisfies the specifications. Our empirical evaluations on systems with a wide variety of disturbances show that the strategies synthesized with our approach lead to high satisfaction probabilities and validate the theoretical guarantees.more » « less
-
null (Ed.)This paper addresses the problem of online inverse reinforcement learning for nonlinear systems with modeling uncertainties and additive disturbances. In the developed approach, the learner measures state and input trajectories of the demonstrator and identifies its unknown reward function online. Sub-optimality introduced in the measured trajectories by the unknown external disturbance is compensated for using a novel model-based inverse reinforcement learning approach. The learner estimates the external disturbances and uses them to identify the dynamic model of the demonstrator. The learned model along with the observed sub-optimal trajectories are used for reward function estimation.more » « less
-
Summary This paper proposes an intermittent model‐free learning algorithm for linear time‐invariant systems, where the control policy and transmission decisions are co‐designed simultaneously while also being subjected to worst‐case disturbances. The control policy is designed by introducing an internal dynamical system to further reduce the transmission rate and provide bandwidth flexibility in cyber‐physical systems. Moreover, aQ‐learning algorithm with two actors and a single critic structure is developed to learn the optimal parameters of aQ‐function. It is shown by using an impulsive system approach that the closed‐loop system has an asymptotically stable equilibrium and that no Zeno behavior occurs. Furthermore, a qualitative performance analysis of the model‐free dynamic intermittent framework is given and shows the degree of suboptimality concerning the optimal continuous updated controller. Finally, a numerical simulation of an unknown system is carried out to highlight the efficacy of the proposed framework.more » « less
-
Abstract The auditory and vestibular systems exhibit remarkable sensitivity of detection, responding to deflections on the order of angstroms, even in the presence of biological noise. The auditory system exhibits high temporal acuity and frequency selectivity, allowing us to make sense of the acoustic world around us. As the acoustic signals of interest span many orders of magnitude in both amplitude and frequency, this system relies heavily on nonlinearities and power-law scaling. The vestibular system, which detects ground-borne vibrations and creates the sense of balance, exhibits highly sensitive, broadband detection. It likewise requires high temporal acuity so as to allow us to maintain balance while in motion. The behavior of these sensory systems has been extensively studied in the context of dynamical systems theory, with many empirical phenomena described by critical dynamics. Other phenomena have been explained by systems in the chaotic regime, where weak perturbations drastically impact the future state of the system. Using a Hopf oscillator as a simple numerical model for a sensory element in these systems, we explore the intersection of the two types of dynamical phenomena. We identify the relative tradeoffs between different detection metrics, and propose that, for both types of sensory systems, the instabilities giving rise to chaotic dynamics improve signal detection.more » « less
