Cargando…

Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder

An adaptive deep neural network is used in an inverse system identification setting to approximate the inverse of a nonlinear plant with the aim of constituting the plant controller by copying to the latter the weights and architecture of the converging deep neural network. This deep learning (DL) a...

Descripción completa

Detalles Bibliográficos
Autores principales: Alwan, Nuha A. S., Hussain, Zahir M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9415480/
https://www.ncbi.nlm.nih.gov/pubmed/36015696
http://dx.doi.org/10.3390/s22165935
_version_ 1784776242194546688
author Alwan, Nuha A. S.
Hussain, Zahir M.
author_facet Alwan, Nuha A. S.
Hussain, Zahir M.
author_sort Alwan, Nuha A. S.
collection PubMed
description An adaptive deep neural network is used in an inverse system identification setting to approximate the inverse of a nonlinear plant with the aim of constituting the plant controller by copying to the latter the weights and architecture of the converging deep neural network. This deep learning (DL) approach to the adaptive inverse control (AIC) problem is shown to outperform the adaptive filtering techniques and algorithms normally used in adaptive control, especially when in nonlinear plants. The deeper the controller, the better the inverse function approximation, provided that the nonlinear plant has an inverse and that this inverse can be approximated. Simulation results prove the feasibility of this DL-based adaptive inverse control scheme. The DL-based AIC system is robust to nonlinear plant parameter changes in that the plant output reassumes the value of the reference signal considerably faster than with the adaptive filter counterpart of the deep neural network. The settling and rise times of the step response are shown to improve in the DL-based AIC system.
format Online
Article
Text
id pubmed-9415480
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-94154802022-08-27 Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder Alwan, Nuha A. S. Hussain, Zahir M. Sensors (Basel) Article An adaptive deep neural network is used in an inverse system identification setting to approximate the inverse of a nonlinear plant with the aim of constituting the plant controller by copying to the latter the weights and architecture of the converging deep neural network. This deep learning (DL) approach to the adaptive inverse control (AIC) problem is shown to outperform the adaptive filtering techniques and algorithms normally used in adaptive control, especially when in nonlinear plants. The deeper the controller, the better the inverse function approximation, provided that the nonlinear plant has an inverse and that this inverse can be approximated. Simulation results prove the feasibility of this DL-based adaptive inverse control scheme. The DL-based AIC system is robust to nonlinear plant parameter changes in that the plant output reassumes the value of the reference signal considerably faster than with the adaptive filter counterpart of the deep neural network. The settling and rise times of the step response are shown to improve in the DL-based AIC system. MDPI 2022-08-09 /pmc/articles/PMC9415480/ /pubmed/36015696 http://dx.doi.org/10.3390/s22165935 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Alwan, Nuha A. S.
Hussain, Zahir M.
Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder
title Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder
title_full Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder
title_fullStr Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder
title_full_unstemmed Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder
title_short Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder
title_sort deep learning for robust adaptive inverse control of nonlinear dynamic systems: improved settling time with an autoencoder
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9415480/
https://www.ncbi.nlm.nih.gov/pubmed/36015696
http://dx.doi.org/10.3390/s22165935
work_keys_str_mv AT alwannuhaas deeplearningforrobustadaptiveinversecontrolofnonlineardynamicsystemsimprovedsettlingtimewithanautoencoder
AT hussainzahirm deeplearningforrobustadaptiveinversecontrolofnonlineardynamicsystemsimprovedsettlingtimewithanautoencoder