Saved in:
Bibliographic Details
Main Authors: Thieffry, Maxime, Hache, Alexandre, Yagoubi, Mohamed, Chevrel, Philippe
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.15858
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914963288752128
author Thieffry, Maxime
Hache, Alexandre
Yagoubi, Mohamed
Chevrel, Philippe
author_facet Thieffry, Maxime
Hache, Alexandre
Yagoubi, Mohamed
Chevrel, Philippe
contents This work presents a control-oriented identification scheme for efficient control design and stability analysis of nonlinear systems. Neural networks are used to identify a discrete-time nonlinear state-space model to approximate time-domain input-output behavior of a nonlinear system. The network is constructed such that the identified model is approximately linearizable by feedback, ensuring that the control law trivially follows from the learning stage. After the identification and quasi-linearization procedures, linear control theory comes at hand to design robust controllers and study stability of the closed-loop system. The effectiveness and interest of the methodology are illustrated throughout the paper on popular benchmarks for system identification.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15858
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Identification For Control Based on Neural Networks: Approximately Linearizable Models
Thieffry, Maxime
Hache, Alexandre
Yagoubi, Mohamed
Chevrel, Philippe
Systems and Control
Artificial Intelligence
This work presents a control-oriented identification scheme for efficient control design and stability analysis of nonlinear systems. Neural networks are used to identify a discrete-time nonlinear state-space model to approximate time-domain input-output behavior of a nonlinear system. The network is constructed such that the identified model is approximately linearizable by feedback, ensuring that the control law trivially follows from the learning stage. After the identification and quasi-linearization procedures, linear control theory comes at hand to design robust controllers and study stability of the closed-loop system. The effectiveness and interest of the methodology are illustrated throughout the paper on popular benchmarks for system identification.
title Identification For Control Based on Neural Networks: Approximately Linearizable Models
topic Systems and Control
Artificial Intelligence
url https://arxiv.org/abs/2409.15858