Nonlinear Discrete-Time Observers with Physics-Informed Neural Networks
We use Physics-Informed Neural Networks (PINNs) to solve the discrete-time nonlinear observer state estimation problem. Integrated within a single-step exact observer linearization framework, the proposed PINN approach aims at learning a nonlinear state transformation map by solving a system of inhomogeneous functional equations. The performance of the proposed PINN approach is assessed via two illustrative case studies for which the observer linearizing transformation map can be derived analytically. We also perform an uncertainty quantification analysis for the proposed PINN scheme and we compare it with conventional power-series numerical implementations, which rely on the computation of a power series solution.
Code (0)
등록된 구현이 없습니다.
Tasks
State EstimationUncertainty QuantificationSimilar Papers 제목 키워드 기반
Verifiable Error Bounds for Physics-Informed Neural KKL Observers
This paper proposes a computable state-estimation error bound for learning-based Kazantzis--Kravaris/Luenberger (KKL) observers. Recent work learns the KKL transformation map with a physics-informed neural network (PINN)…
Functional observers with linear error dynamics for discrete-time nonlinear systems, with application to fault diagnosis
This work deals with the problem of designing observers for the estimation of a single function of the states for discrete-time nonlinear systems. Necessary and sufficient conditions for the existence of lower order func…
Fault DetectionFault DiagnosisPINN-Obs: Physics-Informed Neural Network-Based Observer for Nonlinear Dynamical Systems
State estimation for nonlinear dynamical systems is a critical challenge in control and engineering applications, particularly when only partial and noisy measurements are available. This paper introduces a novel Adaptiv…
Learning-based Design of Luenberger Observers for Autonomous Nonlinear Systems
Designing Luenberger observers for nonlinear systems involves the challenging task of transforming the state to an alternate coordinate system, possibly of higher dimensions, where the system is asymptotically stable and…
Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations…