Nonlinear MPC for Offset-Free Tracking of systems learned by GRU Neural Networks

TL;DR

This paper develops a nonlinear Model Predictive Control approach using stable Gated Recurrent Units (GRUs) for offset-free tracking of systems, validated on a pH neutralization process with strong results.

Contribution

It introduces a novel method integrating stable GRUs into Nonlinear MPC for control with theoretical stability guarantees.

Findings

Successful offset-free tracking demonstrated on a pH neutralization process

The approach guarantees closed-loop stability

Remarkable control performance achieved in experiments

Abstract

The use of Recurrent Neural Networks (RNNs) for system identification has recently gathered increasing attention, thanks to their black-box modeling capabilities.Albeit RNNs have been fruitfully adopted in many applications, only few works are devoted to provide rigorous theoretical foundations that justify their use for control purposes. The aim of this paper is to describe how stable Gated Recurrent Units (GRUs), a particular RNN architecture, can be trained and employed in a Nonlinear MPC framework to perform offset-free tracking of constant references with guaranteed closed-loop stability. The proposed approach is tested on a pH neutralization process benchmark, showing remarkable performances.