A New Model-Free Method Combined with Neural Networks for MIMO Systems

TL;DR

This paper introduces a model-free adaptive predictive control method for MIMO systems that leverages neural networks, addressing time delay issues and simplifying controller design for practical engineering applications.

Contribution

It proposes a novel model-free control approach that relaxes assumptions, handles time delays, and integrates neural networks for enhanced nonlinear modeling.

Findings

Outperforms existing MFAC in simulations

Handles time delays effectively in MIMO systems

Simplifies controller design and analysis

Abstract

In this brief, a model-free adaptive predictive control (MFAPC) is proposed. It outperforms the current model-free adaptive control (MFAC) for not only solving the time delay problem in multiple-input multiple-output (MIMO) systems but also relaxing the current rigorous assumptions for sake of a wider applicable range. The most attractive merit of the proposed controller is that the controller design, performance analysis and applications are easy for engineers to realize. Furthermore, the problem of how to choose the matrix {\lambda} is finished by analyzing the function of the closed-loop poles rather than the previous contraction mapping method. Additionally, in view of the nonlinear modeling capability and adaptability of neural networks (NNs), we combine these two classes of algorithms together. The feasibility and several interesting results of the proposed method are shown in simulations.