Browse > Article

A Study on Detecting and Monitoring of Weld Root Gap using Neural Networks  

Kang Sung-In (동명대학교 컴퓨터공학과)
Kim Gwan-Hyung (동명대학교 컴퓨터공학과)
Abstract
Weld root gap is a important fact of a falling-off weld quality in various kind of weld defect. The welding quality can be controlled by monitoring important parameters, such as, the Arc voltage, welding current and welding speed during the welding process. Welding systems use either a vision sensor or an Arc sensor, both of which are unable to control these parameters directly. Therefore, it is difficult to obtain necessary bead geometry without automatically controlling the welding parameters through the sensors. In this paper we propose a novel approach using neural networks for detecting and monitoring of weld root gap and bead shape. Through experiments we demonstrate that the proposed system can be used for real welding processes. The results demonstrate that the system can efficiently estimate the weld bead shape and detect the welding defects.
Keywords
Neural network; Functional link network; Weld root gap; Weld bead shape;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 BY S. LIU and T. A. SIEWERT, 'Metal Transfer in Gas Metal Arc Welding Droplet Rate', Welding Journal, Vol.68, No.2, pp. 52-58, 1989
2 Siger Omatu, Mazuki Khalid and Rubiyah Yusof, Neuro-Control and its Application, Springer, pp. 96-118, pp. 134-166, 1996
3 안재현, 김재웅, '박판 GMA용접에서 단락 주파수를 이용한 이면비드 제어에 관한 연구', 대한용접학회지, 제 13권, 제 4호, 1995년 4월
4 김관형, 강성인, '하이브리드 지능시스템을 이용한 용접 파라메타 보상과 용접 형상 평가에 관한 연구', 한국해양정보통신학회논문지 제9권 6호, pp. 1379-1386, 2005   과학기술학회마을
5 A. Matteson, R. Morris and R. Tate, 'Real-time GMAW Quality Classification using an Artificial Neural Network with Airbone Acoustic Signals as Input', Int. Conf. on Computerization of Welding Information IV, November 3-6, 1992, Orlando, Florida, pp. 189-206
6 Kristinn Andersen, George E. Cook, 'Synchronous Weld Pool Oscillation for Monitoring and Control', IEEE Transactions on Industry Applications. Vol 33, No.2 pp. 464-471, March/April 1997   DOI   ScienceOn
7 Jacek M. Zurada, Introduction to Artificial Neural Systems, West Publishing Company, pp. 163-250,1992
8 Yuedong Chen and R. Du, 'A New Method of Designing Artificial Neural Network For Engineering Monitoring and Diagnosis', Dynamic Systems and Control. Vol. 1, pp. 499-506, ASME 1994