Sage Journals: Discover world-class research

Abstract

In gas metal arc (GMA) welding processes, the geometrical shape and size of the weld pool are utilized to assess the integrity of the weld quality. Monitoring of these geometrical parameters for on-line process control as well as for on-line quality evaluation, however, is an extremely difficult problem. The paper describes the design of a neural network estimator to estimate weld pool sizes for on-line use in quality monitoring and control. The neural network estimator is designed to estimate the weld pool sizes from surface temperatures measured at various points on the top surface of the weldment. The main task of the neural network is to realize the mapping characteristics from the point temperatures to the weld pool sizes through training. The chosen design parameters of the neural network estimator, such as the number of hidden layers and the number of nodes in a layer, are based on an estimation error analysis. A series of bead-on-plate welding experiments were performed to assess the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can estimate the weld pool sizes with satisfactory accuracy.

Get full access to this article

View all access options for this article.

References

Oshima

et al. Observation and digital control of the molten pool in pulsed MIG welding. Welding Internat. 1988, 2(3), 234–240.

Richardson

R. D.

Richardson

R. W.

The measurement of two-dimensional arc weld pool geometry by image analysis. Proceedings of conference on Measurement and control for batch manufacturing, ASME Winter Annual Meeting, 1982, 65–75.

Katz

J. M.

Hardt

D. E.

Ultrasonic measurement of weld penetration. Proceedings of conference on Control of manufacturing processes and robotic systems. ASME Winter Annual Meeting, 1983, 79–95.

Zacksenhouse

Hardt

D. E.

Weld pool impedance identification for size measurement and control. Trans. ASME, J. Dyn. Syst. Measmt Control, 1983, 105, 179–184.

Nomura

Back bead width control in one side SAW using flux copper backing. J. Japan Welding Soc, 1985, 3(3), 471–477.

Ramsey

P. W.

et al. Infrared temperature sensing systems for automatic fusion welding, Welding J., Res. Suppl., 1963, August, 337s–346s.

Lukens

W. E.

Morris

R. A.

Infrared temperature sensing of cooling rates for arc welding control, Welding J., 1982, January, 27–33.

Kozono

et al. Relation between surface temperature and reverse side bead width in girth TIG welding for stainless steel tube. J. Japan Welding Soc, 1986, 4(2), 331–335.

Boo

K. S.

A study on analysis and control of gas metal arc welding process. PhD dissertation, Department of Production Engineering, Korea Advanced Institute of Science and Technology, 1991.

10.

Boo

K. S.

Cho

H. S.

On the determination of a temperature sensor location for monitoring weld pool sizes in GMAW. Welding J., submitted for publication, January 1992.

11.

Andersen

Cook

G. E.

Karsai

Ramaswamy

Artificial neural networks applied to arc welding process modeling and control. IEEE Trans, on Indust. Appl., 1990, 26(5), 824–830.

12.

Friedman

Glickstein

S. S.

An investigation of the thermal response of stationary gas tungsten arc welds. Welding J., Res. Suppl. 1976, December, 408s–420s.

13.

Boo

K. S.

Cho

H. S.

Transient temperature distribution in arc welding of finite thickness plates. Proc. Instn Mech. Engrs, Part B, 1990, 204(B3), 175–183.

14.

Chryssolouris

Guillot

A comparison of statistical and Al approaches to the selection of process parameters in intelligent machining, Trans. ASME, J. Engng Ind., 1990, 112, 122–131.

15.

Fukushima

Miyake

Ito

Neocognitron: A neural network model for a mechanism of visual pattern recognition. IEEE Trans., 1983, SMC-13, 826–834.

16.

Lim

T. G.

Kim

J. H.

Cho

H. S.

Kim

S. K.

A neural network method for recognition of part orientation in a programmable bowl feeder. Proceedings of 11th international conference on Assembly automation, 1990, MS90–832, 1–14.

17.

Morris

R. J. T.

Rubin

L. D.

Tirri

Neural network techniques for object orientation detection: Solution by optimal feedforward network and learning vector quantization approaches. IEEE Trans., Pattern Analysis and Machine Intelligence, 1990, 12(11), 1107–1115.

18.

Widrow

Winter

Neural nets for adaptive filtering and adaptive pattern recognition. Computer, 1988, March, 25–39.

19.

Rauch

H. E.

Winarske

Neural networks for routing communication traffic. IEEE Contr. Syst. Mag., 1988, April, 26–31.

20.

Narendra

K. S.

Parthasarathy

Identification and control of dynamical systems using neural networks. IEEE Trans., Neural Networks, 1990, 1(1), 4–27.

21.

Lim

T. G.

Cho

H. S.

Chang

H. S.

Estimation of nugget size in resistance spot welding using a neural network. Presented at 1991 annual American Welding Society convention.

22.

Rangwala

Dornfeld

Sensor integration using neural networks for intelligent tool condition monitoring. Trans. ASME, J. Engng Ind., 1990, 112, 219–228.

23.

Kawato

et al. Hierarchical neural network model for voluntary movement with application to robotics. IEEE Contr. Syst. Mag., 1988, April, 8–16.

24.

Rumelhart

D. E.

Hinton

G. E.

Williams

R. J.

Learning internal representations by error propagation. In Parallel distributed processing: explorations in the microstructures of cognition, 1986, Vol. 1, 318–362 (MIT Press).

25.

Pao

Y.-H.

Adaptive pattern recognition and neural networks, 1989, Addison-Wesley).

Estimation of Weld Pool Sizes in GMA Welding Process Using Neural Networks

Abstract

Get full access to this article

References