圖形辨識在統計製程管制中是一個重要的議題。因為在管制圖中，不正常的圖形與影響製程的因素間存在著一定程度的相關性。近年來，類神經網路被廣泛且有效地應用於圖形辨識問題上，其中非監督式學習的自適應共振理論II有能力在保留舊有的資訊下學習新的資料，因此能夠解決穩定性以及可塑性之間的兩難問題。自適應共振理論II的參數組合在圖形辨識的成效上扮演著相當重要的角色，但以往的研究大多應用試誤法來決定其參數組合，如此會花去很多時間試誤，且無法保證所得到的結果為近似最佳解。為解決此問題，本研究提出實數型基因演算法整合改良型自適應共振理論II之方法，在決定適合自適應共振理論II進行分群學習的管制圖每個時間點之觀察個數後，再應用實數型基因演算法來學習改良型自適應共振理論II之參數，以求得兼顧分群個數少及正確率高之近似最佳參數組合。研究結果顯示，在管制圖之圖形辨識問題上，應用實數型基因演算法來學習改良型自適應共振理論II之參數，則可獲得較試誤法更優良的參數組合，且達到更佳的分群效果。

Pattern recognition is an important issue in statistical process control field because there are relevance between unnatural patterns and factors which affect the process. Neural networks have been extensively and effectively employed in several pattern recognition problems. Among them, adaptive resonance theory II, an unsupervised neural network, can solve the stability-and-plasticity dilemma problem because it can learn new data without erasing currently stored information. The combination of parameters for adaptive resonance theory II plays an important role of pattern recognition problems. Most researches used time-consuming trial-and-error method, which couldn't obtain an approximately optimum solution under different combinations of parameters. This research integrated adaptive resonance theory II and genetic algorithms method to solve the problem. The study determines the suitable subgroup size in control chart for unsupervised learning of adaptive resonance theory II first, and then uses real-parameter genetic algorithms to obtain approximately optimum combination of parameters for adaptive resonance theory II. This enables a few numbers of clusters and high accuracy. The result shows that both the combination of parameters and the clustering effectiveness will be better than trial-and-error method for pattern recognition problem in control chart by using real-parameter genetic algorithms to obtain parameters of adaptive resonance theory II.

Alwan, L. C., Statistical Process Analysis, McGraw Hill, 2000.
Carpenter, G. A. and Grossberg, S., ART2: self-organisation of stable category recognition codes for analog input patterns, Applied Optics, 26(23), 4919-4930, 1987.
Chang, S. I. and AW, C. A., A neural fuzzy control chart for detecting and classifying process means shifts, International Journal of Production Research, 34(8), 2265-2278, 1996.
Cheng, C. S., A multi-layer neural network model for detecting changes in the process mean, Computers and Industrial Engineering, 28(1) , 51-61, 1995.
Dhillon, I. S., Fan, J., and Guan, Y., Efficient clustering of very large document collections, in Data Mining for Scientific and Engineering Applications, Kluwer
Academic Publishers, 2001.
Duncan, A. J., Quality control and industrial statistics, Irwin, 1986.
Goldberg, D. E., Genetic algorithms in search, optimization, and machine learning, Addison-Wesley, 1989.
Grant, E. L. and Leavenworth, R. S., Statistical quality control, McGraw-Hill, 1996.
Grossberg, S., Adaptive pattern classification and universal recoding, II: feedback, expectation, olfaction, and illusions, Biolog Cybernet, 23(187), 1976.
Guh, R. S., Optimizing feedforward neural networks for control chart pattern recognition through genetic algorithms, International Journal of Pattern Recognition and Artificial Intelligence, 18(2), 75-99, 2004.
Guh, R. S., Real-time pattern recognition in statistical process control: a hybrid neural network decision tree-based approach, Proceedings of the Institution of Mechanical Engineers. Part B. Journal of engineering manufacture, 219(3), 283-298, 2005.
Holland, J. H., Adaptation in natural and artificial systems, University of Michigan Press, 1975.
Janikow, C. Z. and Michalewicz, Z., An experimental comparison of binary and floating point representations in genetic algorithms, Proceedings of the Fourth International Conference on Genetic Algorithms, 31-36, 1991.
Montgomery, D. C., Introduction to statistical quality control, John Wiley & Sons, 2005.
Nelson, L. S., The Shewhart control chart-tests for special causes, Journal of Quality Technology, 16(4), 237-239, 1984.
Page, E. S., Continuous inspection schemes, Biometrika, 41(1), 100-115, 1954.
Pham, D. T. and Chan, A. B., Unsupervised adaptive resonance theory neural networks for control chart pattern recognition, Proceedings of the Institution of Mechanical
Engineers. Part B. Journal of engineering manufacture, 215(1), 59-67, 2001.
Pham, D. T. and Chan, A. B., Control chart pattern recognition using a new type of self-organizing neural network, Proceedings of the Institution of Mechanical Engineers. Part I. Journal of Systems and Control Engineering, 212(1), 115-127, 1998.
Pugh, G. A., A comparison of neural networks to SPC charts, Computers and Industrial Engineering, 21(1-4), 253-255, 1991.
Roberts, S. W., Control chart tests based on geometric moving averages, Technometrics, 42(1), 97-102, 1959.
Western Electric, Statistical quality control handbook, Western Electric Corporation, 1956.