Recurrent Neural Network-based Internal Model Control design for stable nonlinear systems
This work addresses control system design for engineers dealing with nonlinear dynamics, but it is incremental as it applies existing neural network methods to a specific control architecture.
The paper tackles the design of Internal Model Control for stable nonlinear systems by using gated Recurrent Neural Networks to model the plant and approximate its inverse, ensuring closed-loop stability and handling control saturation, with testing on a Quadruple Tank benchmark showing remarkable performance.
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.