A Novel Control Strategy for Uninterruptible Power Supply Based on Backstepping and Fuzzy Neural Network

This paper proposes a novel control strategy for controlling the uninterruptible power supply (UPS) inverter, which is based on backstepping control theory combined with a fuzzy neural network (FNN). The advantage of backstepping control is that it can decompose a complex system into multiple subsys...

Full description

Bibliographic Details
Main Authors: Yanfei Dong, Guoyong Zhang, Guofeng He, Wenjie Si
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10013671/
_version_ 1797902195779174400
author Yanfei Dong
Guoyong Zhang
Guofeng He
Wenjie Si
author_facet Yanfei Dong
Guoyong Zhang
Guofeng He
Wenjie Si
author_sort Yanfei Dong
collection DOAJ
description This paper proposes a novel control strategy for controlling the uninterruptible power supply (UPS) inverter, which is based on backstepping control theory combined with a fuzzy neural network (FNN). The advantage of backstepping control is that it can decompose a complex system into multiple subsystems, stabilize the control object according to Lyapunov stability theory, and simplify the controller design. However, it requires prior knowledge of multiple system parameters. FNN can approximate arbitrary nonlinear functions and system errors, which can reduce the parameters required for controller design. Hence, Combining the advantages of both methods, a UPS inverter control method with only a few parameters is designed. Then the sliding mode gain is added to compensate for the fuzzy neural network to reduce the chattering when the system operates and ensure the needed power quality. To verify the effectiveness of the proposed control system, the effectiveness of the proposed method is verified by a simulation experiment platform.
first_indexed 2024-04-10T09:13:52Z
format Article
id doaj.art-0e904cdd808241bba0c634998600c4bc
institution Directory Open Access Journal
issn 2169-3536
language English
last_indexed 2024-04-10T09:13:52Z
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj.art-0e904cdd808241bba0c634998600c4bc2023-02-21T00:02:24ZengIEEEIEEE Access2169-35362023-01-01115306531310.1109/ACCESS.2023.323588510013671A Novel Control Strategy for Uninterruptible Power Supply Based on Backstepping and Fuzzy Neural NetworkYanfei Dong0Guoyong Zhang1https://orcid.org/0000-0003-0746-1419Guofeng He2https://orcid.org/0000-0001-5674-4453Wenjie Si3School of Electrical and Control Engineering, Henan University of Urban Construction, Pingdingshan, ChinaSchool of Electrical and Control Engineering, Henan University of Urban Construction, Pingdingshan, ChinaSchool of Electrical and Control Engineering, Henan University of Urban Construction, Pingdingshan, ChinaSchool of Electrical and Control Engineering, Henan University of Urban Construction, Pingdingshan, ChinaThis paper proposes a novel control strategy for controlling the uninterruptible power supply (UPS) inverter, which is based on backstepping control theory combined with a fuzzy neural network (FNN). The advantage of backstepping control is that it can decompose a complex system into multiple subsystems, stabilize the control object according to Lyapunov stability theory, and simplify the controller design. However, it requires prior knowledge of multiple system parameters. FNN can approximate arbitrary nonlinear functions and system errors, which can reduce the parameters required for controller design. Hence, Combining the advantages of both methods, a UPS inverter control method with only a few parameters is designed. Then the sliding mode gain is added to compensate for the fuzzy neural network to reduce the chattering when the system operates and ensure the needed power quality. To verify the effectiveness of the proposed control system, the effectiveness of the proposed method is verified by a simulation experiment platform.https://ieeexplore.ieee.org/document/10013671/Power qualityfuzzy neural network (FNN)backstepping controluninterruptible power supply (UPS)
spellingShingle Yanfei Dong
Guoyong Zhang
Guofeng He
Wenjie Si
A Novel Control Strategy for Uninterruptible Power Supply Based on Backstepping and Fuzzy Neural Network
IEEE Access
Power quality
fuzzy neural network (FNN)
backstepping control
uninterruptible power supply (UPS)
title A Novel Control Strategy for Uninterruptible Power Supply Based on Backstepping and Fuzzy Neural Network
title_full A Novel Control Strategy for Uninterruptible Power Supply Based on Backstepping and Fuzzy Neural Network
title_fullStr A Novel Control Strategy for Uninterruptible Power Supply Based on Backstepping and Fuzzy Neural Network
title_full_unstemmed A Novel Control Strategy for Uninterruptible Power Supply Based on Backstepping and Fuzzy Neural Network
title_short A Novel Control Strategy for Uninterruptible Power Supply Based on Backstepping and Fuzzy Neural Network
title_sort novel control strategy for uninterruptible power supply based on backstepping and fuzzy neural network
topic Power quality
fuzzy neural network (FNN)
backstepping control
uninterruptible power supply (UPS)
url https://ieeexplore.ieee.org/document/10013671/
work_keys_str_mv AT yanfeidong anovelcontrolstrategyforuninterruptiblepowersupplybasedonbacksteppingandfuzzyneuralnetwork
AT guoyongzhang anovelcontrolstrategyforuninterruptiblepowersupplybasedonbacksteppingandfuzzyneuralnetwork
AT guofenghe anovelcontrolstrategyforuninterruptiblepowersupplybasedonbacksteppingandfuzzyneuralnetwork
AT wenjiesi anovelcontrolstrategyforuninterruptiblepowersupplybasedonbacksteppingandfuzzyneuralnetwork
AT yanfeidong novelcontrolstrategyforuninterruptiblepowersupplybasedonbacksteppingandfuzzyneuralnetwork
AT guoyongzhang novelcontrolstrategyforuninterruptiblepowersupplybasedonbacksteppingandfuzzyneuralnetwork
AT guofenghe novelcontrolstrategyforuninterruptiblepowersupplybasedonbacksteppingandfuzzyneuralnetwork
AT wenjiesi novelcontrolstrategyforuninterruptiblepowersupplybasedonbacksteppingandfuzzyneuralnetwork