Recurrent Neural Network-based Internal Model Control design for stable nonlinear systems

TL;DR

This paper presents a novel control scheme using gated recurrent neural networks to model and invert nonlinear, stable systems, ensuring stability and low computational cost, demonstrated on a benchmark system.

Contribution

It introduces a recurrent neural network-based internal model control method that guarantees stability and handles control saturation in nonlinear systems.

Findings

Achieved stable control of a quadruple tank system

Demonstrated robustness to control variable saturation

Outperformed alternative control methods in benchmarks

Abstract

Owing to their superior modeling capabilities, gated Recurrent Neural Networks, such as Gated Recurrent Units (GRUs) and Long Short-Term Memory networks (LSTMs), have become popular tools for learning dynamical systems. This paper aims to discuss how these networks can be adopted for the synthesis of Internal Model Control (IMC) architectures. To this end, first a gated recurrent network is used to learn a model of the unknown input-output stable plant. Then, a controller gated recurrent network is trained to approximate the model inverse. The stability of these networks, ensured by means of a suitable training procedure, allows to guarantee the input-output closed-loop stability. The proposed scheme is able to cope with the saturation of the control variables, and can be deployed on low-power embedded controllers, as it requires limited online computations. The approach is then tested on the Quadruple Tank benchmark system and compared to alternative control laws, resulting in remarkable closed-loop performances.