Finite‐time sliding mode synchronisation of a fractional‐order hyperchaotic system optimised using a differential evolution algorithm with dual neural networks

Abstract To solve the synchronisation problem associated with fractional‐order hyperchaotic systems, in this study, a new dual‐neural network finite‐time sliding mode control method was developed, and a differential evolution algorithm was used to optimise the switching gain, control parameters, and...

Full description

Bibliographic Details
Main Authors: Keyong Shao, Ao Feng, Tingting Wang, Wenju Li, Jilu Jiang
Format: Article
Language:English
Published: Wiley 2023-05-01
Series:IET Networks
Subjects:
Online Access:https://doi.org/10.1049/ntw2.12069
_version_ 1797828093577003008
author Keyong Shao
Ao Feng
Tingting Wang
Wenju Li
Jilu Jiang
author_facet Keyong Shao
Ao Feng
Tingting Wang
Wenju Li
Jilu Jiang
author_sort Keyong Shao
collection DOAJ
description Abstract To solve the synchronisation problem associated with fractional‐order hyperchaotic systems, in this study, a new dual‐neural network finite‐time sliding mode control method was developed, and a differential evolution algorithm was used to optimise the switching gain, control parameters, and sliding mode surface parameters, greatly reducing chattering problems in sliding mode controllers. By using the developed method, the complete synchronisation of the drive system and the response system of a fractional‐order hyperchaotic system was realised in a finite time; moreover, the stability of the error system under this method was proved by using Lyapunov stability theorem. Numerical simulation results verified the feasibility and superiority of the method.
first_indexed 2024-04-09T12:58:52Z
format Article
id doaj.art-077b4aa3c94844bfbf2652a2fbc9e46a
institution Directory Open Access Journal
issn 2047-4954
2047-4962
language English
last_indexed 2024-04-09T12:58:52Z
publishDate 2023-05-01
publisher Wiley
record_format Article
series IET Networks
spelling doaj.art-077b4aa3c94844bfbf2652a2fbc9e46a2023-05-13T04:59:21ZengWileyIET Networks2047-49542047-49622023-05-01123879710.1049/ntw2.12069Finite‐time sliding mode synchronisation of a fractional‐order hyperchaotic system optimised using a differential evolution algorithm with dual neural networksKeyong Shao0Ao Feng1Tingting Wang2Wenju Li3Jilu Jiang4School of Electrical Information&Engineering Northeast Petroleum University Daqing ChinaSchool of Electrical Information&Engineering Northeast Petroleum University Daqing ChinaSchool of Electrical Information&Engineering Northeast Petroleum University Daqing ChinaSchool of Electrical Information&Engineering Northeast Petroleum University Daqing ChinaSchool of Electrical Information&Engineering Northeast Petroleum University Daqing ChinaAbstract To solve the synchronisation problem associated with fractional‐order hyperchaotic systems, in this study, a new dual‐neural network finite‐time sliding mode control method was developed, and a differential evolution algorithm was used to optimise the switching gain, control parameters, and sliding mode surface parameters, greatly reducing chattering problems in sliding mode controllers. By using the developed method, the complete synchronisation of the drive system and the response system of a fractional‐order hyperchaotic system was realised in a finite time; moreover, the stability of the error system under this method was proved by using Lyapunov stability theorem. Numerical simulation results verified the feasibility and superiority of the method.https://doi.org/10.1049/ntw2.12069differential evolution algorithmfinite‐time sliding mode controllerfractional hyperchaotic systemradial basis function neural network (RBFNN)recurrent neural network (RNN)
spellingShingle Keyong Shao
Ao Feng
Tingting Wang
Wenju Li
Jilu Jiang
Finite‐time sliding mode synchronisation of a fractional‐order hyperchaotic system optimised using a differential evolution algorithm with dual neural networks
IET Networks
differential evolution algorithm
finite‐time sliding mode controller
fractional hyperchaotic system
radial basis function neural network (RBFNN)
recurrent neural network (RNN)
title Finite‐time sliding mode synchronisation of a fractional‐order hyperchaotic system optimised using a differential evolution algorithm with dual neural networks
title_full Finite‐time sliding mode synchronisation of a fractional‐order hyperchaotic system optimised using a differential evolution algorithm with dual neural networks
title_fullStr Finite‐time sliding mode synchronisation of a fractional‐order hyperchaotic system optimised using a differential evolution algorithm with dual neural networks
title_full_unstemmed Finite‐time sliding mode synchronisation of a fractional‐order hyperchaotic system optimised using a differential evolution algorithm with dual neural networks
title_short Finite‐time sliding mode synchronisation of a fractional‐order hyperchaotic system optimised using a differential evolution algorithm with dual neural networks
title_sort finite time sliding mode synchronisation of a fractional order hyperchaotic system optimised using a differential evolution algorithm with dual neural networks
topic differential evolution algorithm
finite‐time sliding mode controller
fractional hyperchaotic system
radial basis function neural network (RBFNN)
recurrent neural network (RNN)
url https://doi.org/10.1049/ntw2.12069
work_keys_str_mv AT keyongshao finitetimeslidingmodesynchronisationofafractionalorderhyperchaoticsystemoptimisedusingadifferentialevolutionalgorithmwithdualneuralnetworks
AT aofeng finitetimeslidingmodesynchronisationofafractionalorderhyperchaoticsystemoptimisedusingadifferentialevolutionalgorithmwithdualneuralnetworks
AT tingtingwang finitetimeslidingmodesynchronisationofafractionalorderhyperchaoticsystemoptimisedusingadifferentialevolutionalgorithmwithdualneuralnetworks
AT wenjuli finitetimeslidingmodesynchronisationofafractionalorderhyperchaoticsystemoptimisedusingadifferentialevolutionalgorithmwithdualneuralnetworks
AT jilujiang finitetimeslidingmodesynchronisationofafractionalorderhyperchaoticsystemoptimisedusingadifferentialevolutionalgorithmwithdualneuralnetworks