Neural Observer with Lyapunov Stability Guarantee for Uncertain Nonlinear Systems

TL;DR

This paper introduces a neural network-based observer for uncertain nonlinear systems that guarantees stability and observability, with proven convergence and verified effectiveness through simulations on various models.

Contribution

It presents a novel neural observer design with Lyapunov stability guarantees for uncertain nonlinear systems, integrating active disturbance rejection and LMI-based analysis.

Findings

Neural observer achieves exponential convergence in uncertain systems.

Stability and observability conditions are established via LMIs.

Simulation results confirm effectiveness on diverse nonlinear models.

Abstract

In this paper, we propose a novel nonlinear observer based on neural networks, called neural observer, for observation tasks of linear time-invariant (LTI) systems and uncertain nonlinear systems. In particular, the neural observer designed for uncertain systems is inspired by the active disturbance rejection control, which can measure the uncertainty in real-time. The stability analysis (e.g., exponential convergence rate) of LTI and uncertain nonlinear systems (involving neural observers) are presented and guaranteed, where it is shown that the observation problems can be solved only using the linear matrix inequalities (LMIs). Also, it is revealed that the observability and controllability of the system matrices are required to demonstrate the existence of solutions of LMIs. Finally, the effectiveness of neural observers is verified on three simulation cases, including the X-29A aircraft model, the nonlinear pendulum, and the four-wheel steering vehicle.