Real time welding parameter prediction for desired character performance

Hang Dong; Ming Cong; Yuming Zhang; Yukang Liu; Heping Chen

doi:10.1109/ICRA.2017.7989211

Real time welding parameter prediction for desired character performance

Hang Dong, Ming Cong, Yuming Zhang, Yukang Liu, Heping Chen

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

10 Scopus citations

Abstract

In arc welding processes, real time control algorithms have to be developed in order to achieve desired weld quality. However, there could exist big uncertainties and noise in the process, which nullifies the conventional online control method. Besides, due to the modelling difficulty and low experimental efficiency, this task is usually performed offline. In this paper, a real time parameter optimization method is developed to find the optimal welding parameters to achieve desired characteristic performance. Gaussian Process Regression (GPR), a non-parametric modelling technique, is employed to model the relationship between input welding parameters and output characteristic performance. The GPR surrogated Bayesian Optimization Algorithm (GPRBOA) is proposed to optimize the welding parameters. Lower Confidence Bound (LCB) and Upper Confidence Bound (UCB) acquisition functions are utilized. Gas tungsten arc welding experiments were performed and the corresponding experimental data are collected and utilized to validate the proposed modelling method. The predicted characteristic performance is compared with the original data and it shows that the modelling method can accurately predict the weld bead geometry. The control algorithms were demonstrated and the results are presented. This paper opens a door for real time parameter tuning to achieve desired performance, hence the proposed method will innovate the arc welding process.

Original language	English
Title of host publication	ICRA 2017 - IEEE International Conference on Robotics and Automation
Pages	1794-1799
Number of pages	6
ISBN (Electronic)	9781509046331
DOIs	https://doi.org/10.1109/ICRA.2017.7989211
State	Published - Jul 21 2017
Event	2017 IEEE International Conference on Robotics and Automation, ICRA 2017 - Singapore, Singapore Duration: May 29 2017 → Jun 3 2017

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
Volume	0
ISSN (Print)	1050-4729

Conference

Conference	2017 IEEE International Conference on Robotics and Automation, ICRA 2017
Country/Territory	Singapore
City	Singapore
Period	5/29/17 → 6/3/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Funding

H. Dong and M. Cong∗ (corresponding author) are with the Department of Mechanical Engineering, Dalian University of Technology, Email: [email protected], Tel. (+86)13130491926 Y. Zhang and Y. Liu are with the Department of Electrical and Computer Engineering, University of Kentucky, Email: [email protected] H. Chen∗ (corresponding author) is with the Ingram School of Engineering, Texas State University, Email: [email protected] *This work is supported by Key Scientific and Technological Project of Liaoning Province (No. 2015080009-201) to M. Cong.

Funders	Funder number
University of Kentucky
Harvard School of Engineering and Applied Sciences
Department of Mechanical Engineering, College of Engineering, Michigan State University
Southwest Texas State University
Dalian University of Technology	13130491926, +86
Department of Electrical Engineering, Chulalongkorn University
Humanity and Social Science Foundation of Department of Education of Liaoning Province	2015080009-201

ASJC Scopus subject areas

Software
Artificial Intelligence
Electrical and Electronic Engineering
Control and Systems Engineering

Access to Document

10.1109/ICRA.2017.7989211

Cite this

@inproceedings{eb0238b19f15489988c9519c84a4e9af,

title = "Real time welding parameter prediction for desired character performance",

abstract = "In arc welding processes, real time control algorithms have to be developed in order to achieve desired weld quality. However, there could exist big uncertainties and noise in the process, which nullifies the conventional online control method. Besides, due to the modelling difficulty and low experimental efficiency, this task is usually performed offline. In this paper, a real time parameter optimization method is developed to find the optimal welding parameters to achieve desired characteristic performance. Gaussian Process Regression (GPR), a non-parametric modelling technique, is employed to model the relationship between input welding parameters and output characteristic performance. The GPR surrogated Bayesian Optimization Algorithm (GPRBOA) is proposed to optimize the welding parameters. Lower Confidence Bound (LCB) and Upper Confidence Bound (UCB) acquisition functions are utilized. Gas tungsten arc welding experiments were performed and the corresponding experimental data are collected and utilized to validate the proposed modelling method. The predicted characteristic performance is compared with the original data and it shows that the modelling method can accurately predict the weld bead geometry. The control algorithms were demonstrated and the results are presented. This paper opens a door for real time parameter tuning to achieve desired performance, hence the proposed method will innovate the arc welding process.",

author = "Hang Dong and Ming Cong and Yuming Zhang and Yukang Liu and Heping Chen",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on Robotics and Automation, ICRA 2017 ; Conference date: 29-05-2017 Through 03-06-2017",

year = "2017",

month = jul,

day = "21",

doi = "10.1109/ICRA.2017.7989211",

language = "English",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

pages = "1794--1799",

booktitle = "ICRA 2017 - IEEE International Conference on Robotics and Automation",

}

Dong, H, Cong, M, Zhang, Y, Liu, Y & Chen, H 2017, Real time welding parameter prediction for desired character performance. in ICRA 2017 - IEEE International Conference on Robotics and Automation., 7989211, Proceedings - IEEE International Conference on Robotics and Automation, vol. 0, pp. 1794-1799, 2017 IEEE International Conference on Robotics and Automation, ICRA 2017, Singapore, Singapore, 5/29/17. https://doi.org/10.1109/ICRA.2017.7989211

Real time welding parameter prediction for desired character performance. / Dong, Hang; Cong, Ming; Zhang, Yuming et al.
ICRA 2017 - IEEE International Conference on Robotics and Automation. 2017. p. 1794-1799 7989211 (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 0).

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

TY - GEN

T1 - Real time welding parameter prediction for desired character performance

AU - Dong, Hang

AU - Cong, Ming

AU - Zhang, Yuming

AU - Liu, Yukang

AU - Chen, Heping

PY - 2017/7/21

Y1 - 2017/7/21

N2 - In arc welding processes, real time control algorithms have to be developed in order to achieve desired weld quality. However, there could exist big uncertainties and noise in the process, which nullifies the conventional online control method. Besides, due to the modelling difficulty and low experimental efficiency, this task is usually performed offline. In this paper, a real time parameter optimization method is developed to find the optimal welding parameters to achieve desired characteristic performance. Gaussian Process Regression (GPR), a non-parametric modelling technique, is employed to model the relationship between input welding parameters and output characteristic performance. The GPR surrogated Bayesian Optimization Algorithm (GPRBOA) is proposed to optimize the welding parameters. Lower Confidence Bound (LCB) and Upper Confidence Bound (UCB) acquisition functions are utilized. Gas tungsten arc welding experiments were performed and the corresponding experimental data are collected and utilized to validate the proposed modelling method. The predicted characteristic performance is compared with the original data and it shows that the modelling method can accurately predict the weld bead geometry. The control algorithms were demonstrated and the results are presented. This paper opens a door for real time parameter tuning to achieve desired performance, hence the proposed method will innovate the arc welding process.

AB - In arc welding processes, real time control algorithms have to be developed in order to achieve desired weld quality. However, there could exist big uncertainties and noise in the process, which nullifies the conventional online control method. Besides, due to the modelling difficulty and low experimental efficiency, this task is usually performed offline. In this paper, a real time parameter optimization method is developed to find the optimal welding parameters to achieve desired characteristic performance. Gaussian Process Regression (GPR), a non-parametric modelling technique, is employed to model the relationship between input welding parameters and output characteristic performance. The GPR surrogated Bayesian Optimization Algorithm (GPRBOA) is proposed to optimize the welding parameters. Lower Confidence Bound (LCB) and Upper Confidence Bound (UCB) acquisition functions are utilized. Gas tungsten arc welding experiments were performed and the corresponding experimental data are collected and utilized to validate the proposed modelling method. The predicted characteristic performance is compared with the original data and it shows that the modelling method can accurately predict the weld bead geometry. The control algorithms were demonstrated and the results are presented. This paper opens a door for real time parameter tuning to achieve desired performance, hence the proposed method will innovate the arc welding process.

UR - http://www.scopus.com/inward/record.url?scp=85027983203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027983203&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2017.7989211

DO - 10.1109/ICRA.2017.7989211

M3 - Conference contribution

AN - SCOPUS:85027983203

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 1794

EP - 1799

BT - ICRA 2017 - IEEE International Conference on Robotics and Automation

T2 - 2017 IEEE International Conference on Robotics and Automation, ICRA 2017

Y2 - 29 May 2017 through 3 June 2017

ER -

Real time welding parameter prediction for desired character performance

Abstract

Publication series

Conference

Bibliographical note

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this