Abstract
The potential of using neural networks in TIG welding has been investigated. It has been successfully demonstrated by using a commercial package, BRAIN-MA KER, on an IBM PC that the feed forward multilayer neural network, trained by the back-propagation algorithm with suitable structures, can give satisfactory predictions for both manual and mechanised TIG Welding. A neural network has been trained to predict the welding conditions (procedure) necessary to produce a good quality weld. The types of defect arising by the use of other welding conditions are also predicted. The feasibility of incorporating a neural network into a welding control system is also discussed.
Get full access to this article
View all access options for this article.
References
1.
Alspector, J.
1989 . 'Neural-style microsystems that learn ', IEEE Communications Magazine , Nov, 29 -36 .
2.
Anon
, 1989 a 'Computerized documentation benefits welding operation ', Welding J , Dec, 59 -60 .
3.
Anon.
1989 b. BrainMaker, User's guide and reference manual (3 rd Edn), California Scientific Software .
4.
Bernasek, M.
1989 . 'Welding procedure review using a personal computer' ,
Welding J.
, May, 43 -46 .
5.
Brown, M.B.
1990 . 'Neural network research in British Aerospace' , Third European Seminar on Neural Computing , IBC Tech Services, London , UK.
6.
Bykat, A.
, and
Schmidt, R.J.
1989 . 'A diagnostic expert system for straight-tube welding machines ', Welding J , July, 40 -43 .
7.
Hecht-Nielsen, R.
1989 . 'Theory of the back-propagation neural network' , Proc IEEE 1989 Int Conf Neural Networks , I -593 -605 .
8.
Kuhne, A.H.
,
Cary, H.B.
, and
Prinz, F.B.
1987 . 'An expert system for robotic arc welding' , Welding J , Nov, 21 -25 .
9.
McClelland, J.L.
, and
Rumelhart, D.E.
(and the
Pdp
Research Group), 1986 . 'Parallel Distributed Processing ', Vols 1 and 2, MIT Press .
10.
McCord Nelson, M.
, and
Illingworth, W.I.
1991 . A Practical Guide to Neural Nets , Addison-Wesley Publishing Co , Reading, MA .
11.
Roth, M.W.
1990 . 'Survey of neural network technology for automatic testing recognition' , IEEE Trans on Neural Networks , 1 , 28 -43 .
12.
Rumelhart, D.E.
,
Hinton, G.E.
, and
Williams, R.J.
1986 . 'Learning representations by back-propagating errors ', Nature , 323 , Oct, 533 -536 .