Adaptive Contraction-based Control of Uncertain Nonlinear Processes using Neural Networks

TL;DR

This paper presents an adaptive neural network-based contraction control method for uncertain nonlinear processes, enabling offset-free tracking and improved convergence by online learning of system parameters.

Contribution

It introduces a novel integrated learning and control framework combining neural networks with contraction-based control for uncertain nonlinear systems.

Findings

Achieves offset-free tracking in uncertain nonlinear systems.

Demonstrates improved convergence rates with adaptive neural networks.

Provides an illustrative example validating the approach.

Abstract

Driven by the flexible manufacturing trend in the process control industry and the uncertain nature of chemical process models, this article aims to achieve offset-free tracking for a family of uncertain nonlinear systems (e.g., using process models with parametric uncertainties) with adaptable performance. The proposed adaptive control approach incorporates into the control loop an adaptive neural network embedded contraction-based controller (to ensure convergence to time-varying references) and an online parameter identification module coupled with reference generation (to ensure modelled parameters converge those of the physical system). The integrated learning and control approach involves training a state and parameter dependent neural network to learn a contraction metric parameterized by the uncertain parameter and a differential feedback gain. This neural network is then embedded in an adaptive contraction-based control law which is updated by parameter estimates online. As uncertain parameter estimates converge to the corresponding physical values, offset-free tracking, simultaneously with improved convergence rates, can be achieved, resulting in a flexible, efficient and less conservative approach to the reference tracking control of uncertain nonlinear processes. An illustrative example is included to demonstrate the overall approach. An illustrative example is included to demonstrate the overall approach.