Pattern recognition systems made up of independent multi-layer perceptrons and learning-vector-quantization neural network modules have been developed for classifying control chart patterns. These composite pattern recognition systems have better classification capabilities than their individual modules. The paper describes the structures of these pattern recognition systems and the results obtained on using them.
Get full access to this article
View all access options for this article.
References
1.
OwenM.SPC and continuous improvement, IFS, Bedford, 1989, p. 149 (Springer Verlag, London).
2.
LippmannR. P.Pattern classification using neural networks. IEEE Communication Magazine, 1989, 47–64.
3.
ChengC.Group technology and expert system concepts applied to statistical process control in small batch manufacturing. PhD dissertation, Graduate College, Arizona State University, Tempe, Arizona, 1989.
4.
SwiftJ. A.Development of a knowledge based expert system for control chart pattern recognition analysis. PhD dissertation, Graduate College, Oklahoma State University, Stillwater, Oklahoma, 1987.
5.
PhamD. T.OztemelE.A knowledge-based statistical process control system. ICARCV'92, Proceedings of 2nd International Conference on Automation, robotics and computer vision, Singapore, 1992, Vol. 3, pp. INV-4.2.1-INV-4.2.6 (Institution of Engineers, Singapore).
6.
HwarngH. B.HubeleN. F.X-bar chart pattern recognition using neural nets. Proceedings of 45th Annual Quality Congress, American Society for Quality Control, Milwaukee, 1991, pp. 884–889.
7.
PhamD. T.OztemelE.Control chart pattern recognition using neural networks, J. Syst. Engng, 1992, 2 (4), special issue on neural networks, 256–262.
8.
RumelhartD. E.HintonG. E.WilliamsR. J.Learning internal representation by error propagation. In Parallel distributed processingRumelhartD. E.McClellandJ. L.), 1986, Vol. 1, pp. 312–362 (MIT Press, Cambridge, Ma).
9.
KohonenT.Self organizing feature map. Proc. IEEE, 1990, 78(9), 1464–1480.
10.
PhamD. T.OztemelE.Control chart pattern recognition using learning vector quantization networks. Int. J. Prod. Res., 1993 (in press).
