A TOPSIS based Self-Organizing Double Loop Recurrent Broad Learning System for Uncertain Nonlinear Systems

Wei-Zhong Huang; Yang Zhao; Wei-Bin Hong; Hong-Rui He; Fei Chao; Longzhi Yang; Chih-Min Lin; Xiang Chang; Changjing Shang; Qiang Shen

doi:10.1109/IJCNN55064.2022.9892855

A TOPSIS based Self-Organizing Double Loop Recurrent Broad Learning System for Uncertain Nonlinear Systems

Wei-Zhong Huang, Yang Zhao, Wei-Bin Hong, Hong-Rui He, Fei Chao^*, Longzhi Yang, Chih-Min Lin, Xiang Chang, Changjing Shang, Qiang Shen

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

94 Downloads (Pure)

Abstract

This study proposes an efficient intelligent control structure for uncertain nonlinear systems. The controller is implemented by a sliding mode control framework including a modified broad leaning network (BLS) with a double-loop recurrent structure. In addition, the proposed BLS involves a self-organizing mechanism to increase or decrease the size of the BLS. The technique for order of preference by similarity to ideal solution (TOPSIS) method is used to build the self-organizing mechanism. Moreover, two dynamic thresholds of TOPSIS are automatically determined according to the stability of the controller. One dynamic threshold is used to consider whether to retain or remove existing network neurons in the BLS; and the other is used to generate new neurons, so as to meet the requirements of different control states and save computing resources. To improve the network's dynamic characteristics, a double-loop recurrent structure is further introduced into the self-organizing BLS. The Lyapunov stability function is used to ensure the stability of the control system. The proposed controller is applied to the simulation control of a nonlinear chaotic system and a three-link robot manipulator. The experimental results show that the proposed controller can achieve better control performance against other network-based controllers. The source code of this work is placed at https://github.com/wzhuang-xmu/SODLRBLS.

Original language	English
Title of host publication	2022 International Joint Conference on Neural Networks
Subtitle of host publication	IJCNN
Publisher	IEEE Press
ISBN (Print)	9781728186719
DOIs	https://doi.org/10.1109/IJCNN55064.2022.9892855
Publication status	Published - 30 Sept 2022
Event	Joint Conference on Neural Networks - Centro Congressi, Padova, Italy Duration: 18 Jul 2022 → 23 Jul 2022 Conference number: 2022

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2022-July

Conference

Conference	Joint Conference on Neural Networks
Abbreviated title	IJCNN
Country/Territory	Italy
City	Padova
Period	18 Jul 2022 → 23 Jul 2022

Keywords

Self-organizing network
broad learning system
double loop recurrent neural network
three-links robot manipulator

Access to Document

10.1109/IJCNN55064.2022.9892855

Accepted ManuscriptAccepted author manuscript, 1.5 MBLicence: CC BY

Permanent link

Persistent link

Cite this

Huang, W.-Z., Zhao, Y., Hong, W.-B., He, H.-R., Chao, F., Yang, L., Lin, C.-M., Chang, X., Shang, C., & Shen, Q. (2022). A TOPSIS based Self-Organizing Double Loop Recurrent Broad Learning System for Uncertain Nonlinear Systems. In 2022 International Joint Conference on Neural Networks: IJCNN (Proceedings of the International Joint Conference on Neural Networks; Vol. 2022-July). IEEE Press. https://doi.org/10.1109/IJCNN55064.2022.9892855

@inproceedings{7dab01735a7e4029aeb5b71806818246,

title = "A TOPSIS based Self-Organizing Double Loop Recurrent Broad Learning System for Uncertain Nonlinear Systems",

abstract = "This study proposes an efficient intelligent control structure for uncertain nonlinear systems. The controller is implemented by a sliding mode control framework including a modified broad leaning network (BLS) with a double-loop recurrent structure. In addition, the proposed BLS involves a self-organizing mechanism to increase or decrease the size of the BLS. The technique for order of preference by similarity to ideal solution (TOPSIS) method is used to build the self-organizing mechanism. Moreover, two dynamic thresholds of TOPSIS are automatically determined according to the stability of the controller. One dynamic threshold is used to consider whether to retain or remove existing network neurons in the BLS; and the other is used to generate new neurons, so as to meet the requirements of different control states and save computing resources. To improve the network's dynamic characteristics, a double-loop recurrent structure is further introduced into the self-organizing BLS. The Lyapunov stability function is used to ensure the stability of the control system. The proposed controller is applied to the simulation control of a nonlinear chaotic system and a three-link robot manipulator. The experimental results show that the proposed controller can achieve better control performance against other network-based controllers. The source code of this work is placed at https://github.com/wzhuang-xmu/SODLRBLS.",

keywords = "Self-organizing network, broad learning system, double loop recurrent neural network, three-links robot manipulator",

author = "Wei-Zhong Huang and Yang Zhao and Wei-Bin Hong and Hong-Rui He and Fei Chao and Longzhi Yang and Chih-Min Lin and Xiang Chang and Changjing Shang and Qiang Shen",

note = "Funding Information: This work was supported by the Natural Science Foundation of Fujian Province of China (No. 2021J01002). Publisher Copyright: {\textcopyright} 2022 IEEE.; Joint Conference on Neural Networks, IJCNN ; Conference date: 18-07-2022 Through 23-07-2022",

year = "2022",

month = sep,

day = "30",

doi = "10.1109/IJCNN55064.2022.9892855",

language = "English",

isbn = "9781728186719",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "IEEE Press",

booktitle = "2022 International Joint Conference on Neural Networks",

address = "United States of America",

}

Huang, W-Z, Zhao, Y, Hong, W-B, He, H-R, Chao, F, Yang, L, Lin, C-M, Chang, X , Shang, C & Shen, Q 2022, A TOPSIS based Self-Organizing Double Loop Recurrent Broad Learning System for Uncertain Nonlinear Systems. in 2022 International Joint Conference on Neural Networks: IJCNN. Proceedings of the International Joint Conference on Neural Networks, vol. 2022-July, IEEE Press, Joint Conference on Neural Networks, Padova, Italy, 18 Jul 2022. https://doi.org/10.1109/IJCNN55064.2022.9892855

A TOPSIS based Self-Organizing Double Loop Recurrent Broad Learning System for Uncertain Nonlinear Systems. / Huang, Wei-Zhong; Zhao, Yang; Hong, Wei-Bin et al.
2022 International Joint Conference on Neural Networks: IJCNN. IEEE Press, 2022. (Proceedings of the International Joint Conference on Neural Networks; Vol. 2022-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

TY - GEN

T1 - A TOPSIS based Self-Organizing Double Loop Recurrent Broad Learning System for Uncertain Nonlinear Systems

AU - Huang, Wei-Zhong

AU - Zhao, Yang

AU - Hong, Wei-Bin

AU - He, Hong-Rui

AU - Chao, Fei

AU - Yang, Longzhi

AU - Lin, Chih-Min

AU - Chang, Xiang

AU - Shang, Changjing

AU - Shen, Qiang

N1 - Conference code: 2022

PY - 2022/9/30

Y1 - 2022/9/30

N2 - This study proposes an efficient intelligent control structure for uncertain nonlinear systems. The controller is implemented by a sliding mode control framework including a modified broad leaning network (BLS) with a double-loop recurrent structure. In addition, the proposed BLS involves a self-organizing mechanism to increase or decrease the size of the BLS. The technique for order of preference by similarity to ideal solution (TOPSIS) method is used to build the self-organizing mechanism. Moreover, two dynamic thresholds of TOPSIS are automatically determined according to the stability of the controller. One dynamic threshold is used to consider whether to retain or remove existing network neurons in the BLS; and the other is used to generate new neurons, so as to meet the requirements of different control states and save computing resources. To improve the network's dynamic characteristics, a double-loop recurrent structure is further introduced into the self-organizing BLS. The Lyapunov stability function is used to ensure the stability of the control system. The proposed controller is applied to the simulation control of a nonlinear chaotic system and a three-link robot manipulator. The experimental results show that the proposed controller can achieve better control performance against other network-based controllers. The source code of this work is placed at https://github.com/wzhuang-xmu/SODLRBLS.

AB - This study proposes an efficient intelligent control structure for uncertain nonlinear systems. The controller is implemented by a sliding mode control framework including a modified broad leaning network (BLS) with a double-loop recurrent structure. In addition, the proposed BLS involves a self-organizing mechanism to increase or decrease the size of the BLS. The technique for order of preference by similarity to ideal solution (TOPSIS) method is used to build the self-organizing mechanism. Moreover, two dynamic thresholds of TOPSIS are automatically determined according to the stability of the controller. One dynamic threshold is used to consider whether to retain or remove existing network neurons in the BLS; and the other is used to generate new neurons, so as to meet the requirements of different control states and save computing resources. To improve the network's dynamic characteristics, a double-loop recurrent structure is further introduced into the self-organizing BLS. The Lyapunov stability function is used to ensure the stability of the control system. The proposed controller is applied to the simulation control of a nonlinear chaotic system and a three-link robot manipulator. The experimental results show that the proposed controller can achieve better control performance against other network-based controllers. The source code of this work is placed at https://github.com/wzhuang-xmu/SODLRBLS.

KW - Self-organizing network

KW - broad learning system

KW - double loop recurrent neural network

KW - three-links robot manipulator

UR - http://www.scopus.com/inward/record.url?scp=85140749325&partnerID=8YFLogxK

U2 - 10.1109/IJCNN55064.2022.9892855

DO - 10.1109/IJCNN55064.2022.9892855

M3 - Conference Proceeding (Non-Journal item)

SN - 9781728186719

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2022 International Joint Conference on Neural Networks

PB - IEEE Press

T2 - Joint Conference on Neural Networks

Y2 - 18 July 2022 through 23 July 2022

ER -

A TOPSIS based Self-Organizing Double Loop Recurrent Broad Learning System for Uncertain Nonlinear Systems

Abstract

Publication series

Conference

Keywords

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this