Hybrid deep learning controller for nonlinear systems based on adaptive learning rates

In this paper, a hybrid deep learning neural network controller (HDLNNC) for nonlinear systems is proposed. The proposed controller structure consists of a multi-layer feed-forward neural network, which can be trained based on the hybrid deep learning. The Lyapunov stability criterion is used to dev...

Full description

Saved in:
Bibliographic Details
Published in:International journal of control 2023-07, Vol.96 (7), p.1710-1723
Main Authors: El-Nagar, Ahmad M., Zaki, Ahmad M., Soliman, F. A. S., El-Bardini, Mohammad
Format: Article
Language:English
Subjects:
Controllers
Deep learning
Hebbian learning rule
hybrid deep learning
Kohonen procedure
Lyapunov stability
Multilayers
Neural networks
Nonlinear control
Nonlinear systems
Parameters
Robust control
self-organised map
Stability criteria
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a hybrid deep learning neural network controller (HDLNNC) for nonlinear systems is proposed. The proposed controller structure consists of a multi-layer feed-forward neural network, which can be trained based on the hybrid deep learning. The Lyapunov stability criterion is used to develop an adaptive learning rate due to the learning rate of the updating parameters plays a worthy role in achieving the stability of a system. To show the robustness of the proposed controller and its performance, several tests such as disturbance signals and parameter variations are carried on a numerical example. In this concern, the practical implementation of the proposed HDLNNC is executed on a real system. The results indicate that the proposed controller is able to improve the system performance compared with other existing controllers.
ISSN:0020-7179
1366-5820
DOI:10.1080/00207179.2022.2067080