This paper describes the use of unsupervised adaptive resonance theory ART2 neural networks for recognizing patterns in statistical process control charts. To improve the classification accuracy, three schemes are proposed. The first scheme involves using information on changes between consecutive points in a pattern. The second scheme modifies the ART2 vigilance parameter during training. The third scheme merges class neurons representing the same class after training. The paper gives results which demonstrate the improvements achieved.
PhamD. T.ChanA. B.Control chart patttern recognition using a new type of self-organising neural network. Proc. Instn Mech. Engrs, Part I, Journal of Systems and Control Engineering, 1998, 212(12), 115–127.
3.
SwiftJ. A.Development of knowledge based expert system for control chart pattern recognition analysis. PhD thesis, Graduate College, Oklahoma State University, Stillwater, Oklahoma, 1987.
4.
ChengC.Group technology and expert system concepts applied to statistical process control in small batch manufacturing. PhD thesis, Graduate College, Arizona State University, Tempe, Arizona, 1989.
5.
OztemelE.Integrating expert systems and neural networks for intelligent on-line statistical process control. PhD thesis, Cardiff University, 1992.
6.
PhamD. T.OztemelE.Combining multi-layer perceptrons with heuristics for reliable control chart pattern recognition. In Artificial Intelligence in Engineering (Eds RzevskiG.PastorJ.AdeyR. A.), Vol. VIII, 1993, pp. 801–810 (Computational Mechanics, Southampton).
7.
SmithA. E.YaziciH.Backpropagation neural network approaches to process control: Evaluation and comparison. Technical Report 90–22-47, Department of Engineering Management, University of Missouri-Rolla, Rolla, Missouri, 1992.
8.
HwarngH. B.HubeleN. F.X-bar chart pattern recognition using neural nets. In 45th Annual Quality Congress, American Society for Quality Control, Milwaukee, Wisconsin, 1991, pp. 884–889.
9.
PhamD. T.Neural networks in engineering. In Proceedings of the 9th International Conference on Artificial Intelligence in Engineering, Pennsylvania, 1994, pp. 3–36.
10.
CarpenterG. A.GrossbergS.ART2: Self-organisation of stable category recognition codes for analog input patterns. Appl. Opt., 1987, 26(23), 4919–4930.
11.
PhamD. T.LiuX.Neural Networks for Identification, Prediction and Control, 1995 (Springer-Verlag, London).
