Apply Adaptive Neural Network PID Controllers for a 6DOF Robotic Arm

Meng Chien Wu; Bing Gang Jhong; Mei Yung Chen

doi:10.1109/ICSSE55923.2022.9948251

Apply Adaptive Neural Network PID Controllers for a 6DOF Robotic Arm

Meng Chien Wu, Bing Gang Jhong, Mei Yung Chen

Department of Mechatronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This thesis proposes a novel controller design for a six-axes robotic arm, based on the neural network frame learning mechanism. The controller structure includes five parts. Firstly, we get the training dataset from the actual construction of the six-axis robotic arm. Secondly, the training method of the neural network is based on adaptively adjust the weight value and error between the input layer and the hidden layer. Thirdly, put the training dataset as input of the neural network to train the model. Finally, we use Lyapunov theory to guarantee the stability of the controller design for a six-axis robotic arm, and compare it with PID controller design.

Original language	English
Title of host publication	ICSSE 2022 - 2022 International Conference on System Science and Engineering
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	79-83
Number of pages	5
ISBN (Electronic)	9781665488525
DOIs	https://doi.org/10.1109/ICSSE55923.2022.9948251
Publication status	Published - 2022
Event	2022 International Conference on System Science and Engineering, ICSSE 2022 - Virtual, Online, Taiwan Duration: 2022 May 26 → 2022 May 29

Publication series

Name	ICSSE 2022 - 2022 International Conference on System Science and Engineering

Conference

Conference	2022 International Conference on System Science and Engineering, ICSSE 2022
Country/Territory	Taiwan
City	Virtual, Online
Period	2022/05/26 → 2022/05/29

Keywords

Adaptive Control
Artificial neural network
six-axis robotic arm

ASJC Scopus subject areas

Control and Systems Engineering
Mechanical Engineering
Control and Optimization
Artificial Intelligence
Computer Science Applications
Information Systems

Access to Document

10.1109/ICSSE55923.2022.9948251

Cite this

Wu, M. C., Jhong, B. G., & Chen, M. Y. (2022). Apply Adaptive Neural Network PID Controllers for a 6DOF Robotic Arm. In ICSSE 2022 - 2022 International Conference on System Science and Engineering (pp. 79-83). (ICSSE 2022 - 2022 International Conference on System Science and Engineering). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSSE55923.2022.9948251

Apply Adaptive Neural Network PID Controllers for a 6DOF Robotic Arm. / Wu, Meng Chien; Jhong, Bing Gang; Chen, Mei Yung.
ICSSE 2022 - 2022 International Conference on System Science and Engineering. Institute of Electrical and Electronics Engineers Inc., 2022. p. 79-83 (ICSSE 2022 - 2022 International Conference on System Science and Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Wu, MC, Jhong, BG & Chen, MY 2022, Apply Adaptive Neural Network PID Controllers for a 6DOF Robotic Arm. in ICSSE 2022 - 2022 International Conference on System Science and Engineering. ICSSE 2022 - 2022 International Conference on System Science and Engineering, Institute of Electrical and Electronics Engineers Inc., pp. 79-83, 2022 International Conference on System Science and Engineering, ICSSE 2022, Virtual, Online, Taiwan, 2022/05/26. https://doi.org/10.1109/ICSSE55923.2022.9948251

@inproceedings{dfbb7324033e4a0598cd07fc03a0426d,

title = "Apply Adaptive Neural Network PID Controllers for a 6DOF Robotic Arm",

abstract = "This thesis proposes a novel controller design for a six-axes robotic arm, based on the neural network frame learning mechanism. The controller structure includes five parts. Firstly, we get the training dataset from the actual construction of the six-axis robotic arm. Secondly, the training method of the neural network is based on adaptively adjust the weight value and error between the input layer and the hidden layer. Thirdly, put the training dataset as input of the neural network to train the model. Finally, we use Lyapunov theory to guarantee the stability of the controller design for a six-axis robotic arm, and compare it with PID controller design.",

keywords = "Adaptive Control, Artificial neural network, six-axis robotic arm",

author = "Wu, {Meng Chien} and Jhong, {Bing Gang} and Chen, {Mei Yung}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 International Conference on System Science and Engineering, ICSSE 2022 ; Conference date: 26-05-2022 Through 29-05-2022",

year = "2022",

doi = "10.1109/ICSSE55923.2022.9948251",

language = "English",

series = "ICSSE 2022 - 2022 International Conference on System Science and Engineering",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "79--83",

booktitle = "ICSSE 2022 - 2022 International Conference on System Science and Engineering",

}

TY - GEN

T1 - Apply Adaptive Neural Network PID Controllers for a 6DOF Robotic Arm

AU - Wu, Meng Chien

AU - Jhong, Bing Gang

AU - Chen, Mei Yung

PY - 2022

Y1 - 2022

N2 - This thesis proposes a novel controller design for a six-axes robotic arm, based on the neural network frame learning mechanism. The controller structure includes five parts. Firstly, we get the training dataset from the actual construction of the six-axis robotic arm. Secondly, the training method of the neural network is based on adaptively adjust the weight value and error between the input layer and the hidden layer. Thirdly, put the training dataset as input of the neural network to train the model. Finally, we use Lyapunov theory to guarantee the stability of the controller design for a six-axis robotic arm, and compare it with PID controller design.

AB - This thesis proposes a novel controller design for a six-axes robotic arm, based on the neural network frame learning mechanism. The controller structure includes five parts. Firstly, we get the training dataset from the actual construction of the six-axis robotic arm. Secondly, the training method of the neural network is based on adaptively adjust the weight value and error between the input layer and the hidden layer. Thirdly, put the training dataset as input of the neural network to train the model. Finally, we use Lyapunov theory to guarantee the stability of the controller design for a six-axis robotic arm, and compare it with PID controller design.

KW - Adaptive Control

KW - Artificial neural network

KW - six-axis robotic arm

UR - http://www.scopus.com/inward/record.url?scp=85143401269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85143401269&partnerID=8YFLogxK

U2 - 10.1109/ICSSE55923.2022.9948251

DO - 10.1109/ICSSE55923.2022.9948251

M3 - Conference contribution

AN - SCOPUS:85143401269

T3 - ICSSE 2022 - 2022 International Conference on System Science and Engineering

SP - 79

EP - 83

BT - ICSSE 2022 - 2022 International Conference on System Science and Engineering

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 International Conference on System Science and Engineering, ICSSE 2022

Y2 - 26 May 2022 through 29 May 2022

ER -

Apply Adaptive Neural Network PID Controllers for a 6DOF Robotic Arm

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this