在進行產品的品質管理時，企業經常使用管制圖來監控製程是否出現問題，而隨著科技與技術的進步，許多製程的不良率已大幅下降，面對這些不良率極低的製程，應使用高良率管制圖才能有效偵測變異。CCC-r管制圖為高良率管制圖的一種，主要是透過檢驗出第?個不良品之前的累積檢驗個數來監控製程，其中，r值的設置會影響管制圖的管制表現，不同程度的偏移適用的r值不盡相同，因此，面對瞬息萬變且難以預測的製程情況，僅採用單一r值無法有效監控所有可能的偏移情境。本研究利用CCC-r管制圖結合能夠透過製程狀況動態調整參數的適應性管制技術，發展出變動r值之適應性CCC-r管制圖，根據製程狀態是否穩定來選擇使用的r值以及管制參數，綜合不同r值的優勢，加強管制圖偵測製程變異的能力。此外，r值一般須透過人為主觀決定，使用上較不方便且可能無法達到管制圖的最大效益，為解決此問題，本研究在建構適應性CCC-r管制圖時，利用類神經網路與基因演算法建立一套求解最佳管制參數的流程，首先將製程的平均不良率以及對誤差的可接受度輸入支援向量迴歸、隨機森林以及深度神經網路等類神經網路模型，找出適用於該情況的r值與管制參數，再將結果輸入基因演算法進行最佳化，獲得最佳參數組合，克服參數難以訂定的困境，並確保利用該組參數建立的管制圖在面對不同偏移情境時皆具有一定的效益。透過模擬數據進行驗證後，可以發現單純使用類神經網路時，隨機森林求得的管制參數組合能較快偵測到製程的小幅偏移，面對大偏移時則以深度神經網路求得的管制參數表現最好，而在搭配基因演算法後，又能更進一步提高管制圖的偵測能力，並以隨機森林為基礎之基因演算法求得的管制參數組合擁有最佳績效。最後，本研究利用模擬製程數據進行實例說明，比較變動r值之適應性CCC-r管制圖與CCC-r管制圖的績效表現，結果顯示適應性CCC-r管制圖能更快偵測到製程變異，驗證了此方法在監控高良率製程時的有效性。

In quality management, control chart is one of the effective tools to monitor manufacturing process. The industry uses Cumulative Count of Conforming (CCC)-r control chart to monitor high yield processes, which is based on the number of items inspected until observing r nonconforming ones. The value of r in CCC-r control chart will affect the performance of the control chart. In general, r is determined by the manager subjectively. However, as the manufacturing processes become more complicated, it is more difficult and time-consuming to find the optimal value of r. In this study, we propose an adaptive CCC-r control chart with variable r, which will vary the value of r and control parameters depend on the process information, to improve the sensitivity to shifts in the fraction defectives. In addition, we propose three kinds of neural networks to determine the value of control parameters by support vector regression (SVR), random forest (RF), and deep neural network (DNN), respectively. Then we integrate neural networks with the genetic algorithm (GA) to obtain neural networks based GA. Through the neural networks based GA, we can get the optimal r and control parameters by the defect rate of the process (p0) and the type I error (α). Finally, we compare the adaptive CCC-r control chart with CCC-r control chart. The results show that the adaptive CCC-r control chart with variable r can detect the shift more quickly and RF based GA has the best performance, which means we can get optimal control parameters through that model.

Bouktif, S., Fiaz, A., Ouni, A., & Serhani, M. A. (2018). Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches. Energies, 11(7), Article 1636.
Bourke, P. D. (1991). Detecting a shift in fraction nonconforming using run-length control charts with 100% inspection. Journal of Quality Technology, 23(3), 225-238.
Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123-140.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A. (1984). Classification and Regression Trees. Taylor & Francis Group.
Calvin, T. (1983). Quality control techniques for" zero defects". IEEE Transactions on Components, Hybrids, and Manufacturing Technology, 6(3), 323-328.
Cerrada, M., Zurita, G., Cabrera, D., Sanchez, R. V., Artes, M., & Li, C. (2016). Fault diagnosis in spur gears based on genetic algorithm and random forest. Mechanical Systems and Signal Processing, 70-71, 87-103.
Chan, L. Y., Lai, C. D., Xie, M., & Goh, T. N. (2003). A two-stage decision procedure for monitoring processes with low fraction nonconforming. European Journal of Operational Research, 150(2), 420-436.
Chang, T., & Gan, F. (2001). Cumulative sum charts for high yield processes. Statistica Sinica, 791-805.
Chen, Y. K. (2004). Economic design of X ̅ control charts for non-normal data using variable sampling policy. International Journal of Production Economics, 92(1), 61-74.
Chen, Y. K., Chen, C. Y., & Chiou, K. C. (2011). Cumulative conformance count chart with variable sampling intervals and control limits. Applied Stochastic Models in Business and Industry, 27(4), 410-420.
Chen, Y. K., & Hsieh, K. L. (2007). Hotelling’s T^2 charts with variable sample size and control limit. European Journal of Operational Research, 182(3), 1251-1262.
Cook, D. F., Ragsdale, C. T., & Major, R. (2000). Combining a neural network with a genetic algorithm for process parameter optimization. Engineering Applications of Artificial Intelligence, 13(4), 391-396.
Costa, A. F. B. (1999). X ̅ charts with variable parameters. Journal of Quality Technology, 31(4), 408-416.
Fallah Nezhad, M. S., Shamstabar, Y., & Vali Siar, M. M. (2017). Performance of CCC-r control chart with variable sampling intervals. Journal of Industrial Engineering and Management Studies, 4(2), 19-34.
Georganos, S., Grippa, T., Vanhuysse, S., Lennert, M., Shimoni, M., Kalogirou, S., & Wolff, E. (2018). Less is more: optimizing classification performance through feature selection in a very-high-resolution remote sensing object-based urban application. GIScience & Remote Sensing, 55(2), 221-242.
Goh, T. N. (1987). A Control Chart for Very High Yield Processes. Quality Assurance, 13(1), 18-22.
Hamdia, K. M., Zhuang, X. Y., & Rabczuk, T. (2021). An efficient optimization approach for designing machine learning models based on genetic algorithm. Neural Computing & Applications, 33(6), 1923-1933.
Haq, A. N., Ramanan, T. R., Shashikant, K. S., & Sridharan, R. (2009). A hybrid neural network–genetic algorithm approach for permutation flow shop scheduling. International Journal of Production Research, 48(14), 4217-4231.
He, D., Grigoryan, A., & Sigh, M. (2002). Design of double- and triple-sampling X-bar control charts using genetic algorithms. International Journal of Production Research, 40(6), 1387-1404.
Holland, J. H. (1975). Adaptation in Natural and Artificial Systems. MIT press.
Hsu, C. W., Chang, C. C., & Lin, C. J. (2003). A Practical Guide to Support Vector Classification, Technical Report, Department of Computer Science and Information Engineering, National Taiwan University.
Kadaba, N., Nygard, K. E., & Juell, P. L. (1991). Integration of adaptive machine learning and knowledge-based systems for routing and scheduling applications. Expert Systems with Applications, 2(1), 15-27.
Kilicarslan, S., Celik, M., & Sahin, S. (2021). Hybrid models based on genetic algorithm and deep learning algorithms for nutritional Anemia disease classification. Biomedical Signal Processing and Control, 63, Article 102231.
Kotani, T., Kusukawa, E., & Ohta, H. (2005). Exponentially weighted moving average chart for high-yield processes. Industrial Engineering and Management Systems, 4(1), 75-81.
Kumar, S. (2004). Neural Networks: A Classroom Approach. Tata McGraw-Hill Education.
Kuo, R. J. (2001). A sales forecasting system based on fuzzy neural network with initial weights generated by genetic algorithm. European Journal of Operational Research, 129(3), 496-517.
Liu, J. Y., Xie, M., Goh, T. N., Liu, Q. H., & Yang, Z. H. (2006). Cumulative count of conforming chart with variable sampling intervals. International Journal of Production Economics, 101(2), 286-297.
Majumdar, A., Das, A., Hatua, P., & Ghosh, A. (2016). Optimization of woven fabric parameters for ultraviolet radiation protection and comfort using artificial neural network and genetic algorithm. Neural Computing & Applications, 27(8), 2567-2576.
Montana, D. J., & Davis, L. (1989). Training feedforward neural networks using genetic algorithms. In Proceedings of 11th International Joint Conference on Artificial Intelligence (pp. 762-767). San Mateo, CA: Morgan Kaufmann.
Nair, V., & Hinton, G. E. (2010). Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10) (pp. 807-814).
Niu, G. Q., Yi, X. H., Chen, C., Li, X. Y., Han, D. H., Yan, B., Huang, M. Z., & Ying, G. G. (2020). A novel effluent quality predicting model based on genetic-deep belief network algorithm for cleaner production in a full-scale paper-making wastewater treatment. Journal of Cleaner Production, 265, Article 121787.
Ohta, H., Kusukawa, E., & Rahim, A. (2001). A CCC-r chart for high-yield processes. Quality and Reliability Engineering International, 17(6), 439-446.
Patel, H., Thakkar, A., Pandya, M., & Makwana, K. (2018). Neural network with deep learning architectures. Journal of Information and Optimization Sciences, 39(1), 31-38.
Prabhu, S. S., Montgomery, D. C., & Runger, G. C. (1994). A combined adaptive sample size and sampling interval X ̅ control scheme. Journal of Quality Technology, 26(3), 164-176.
Prabhu, S. S., Runger, G. C., & Keats, J. B. (1993). X ̅ chart with adaptive sample sizes. International Journal of Production Research, 31(12), 2895-2909.
Quinlan, J. R. (1986). Induction of decision trees. Machine Learning, 1(1), 81-106.
Rao, S. S. (1996). Engineering Optimization: Theory and Practice. John Wiley & Sons.
Reynolds, M. R., Amin, R. W., Arnold, J. C., & Nachlas, J. A. (1988). Charts with variable sampling intervals. Technometrics, 30(2), 181-192.
Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386.
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536.
Schaffer, J. D., Caruana, R. A., & Eshelman, L. J. (1990). Using genetic search to exploit the emergent behavior of neural networks. Physica D: Nonlinear Phenomena, 42(1), 244-248.
Schaffer, J. D., Whitley, D., & Eshelman, L. J. (1992). Combinations of genetic algorithms and neural networks: a survey of the state of the art. [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks (pp. 1-37).
Szarka, J. L., & Woodall, W. H. (2011). A Review and perspective on surveillance of Bernoulli processes. Quality and Reliability Engineering International, 27(6), 735-752.
Tagaras, G. (1998). A survey of recent developments in the design of adaptive control charts. Journal of Quality Technology, 30(3), 212-231.
Timofeev, R. (2004). Classification and Regression Trees (CART) Theory and Applications. Humboldt University, Berlin.
Vapnik, V., Golowich, S. E., & Smola, A. (1997). Support vector method for function approximation, regression estimation, and signal processing. In Mozer M.C., Jordan M.I., and Petsche T. (Eds.) Advances in Neural Information Processing Systems 9 (pp. 281-287). MIT Press.
Wu, P. J., & Yang, D. (2021). E-commerce workshop scheduling based on deep learning and genetic algorithm. International Journal of Simulation Modelling, 20(1), 192-200.
Xie, M., & Goh, T. (1997). The use of probability limits for process control based on geometric distribution. International Journal of Quality & Reliability Management, 14(1), 64-73.
Xie, M., Lu, X., Goh, T., & Chan, L. (1999). A quality monitoring and decision‐making scheme for automated production processes. International Journal of Quality & Reliability Management, 16(2), 148-157.
Xie, M., Tang, X., & Goh, T. (2001). On economic design of cumulative count of conforming chart. International Journal of Production Economics, 72(1), 89-97.
Yalkin, C., & Korkmaz, E. E. (2012). Neural network world: A neural network based selection method for genetic algorithms. Neural Network World, 22(6), 495-510.
Zhang, D., Qian, L., Mao, B., Huang, C., Huang, B., & Si, Y. (2018). A data-driven design for fault detection of wind turbines using random forests and XGboost. IEEE Access, 6, 21020-21031.
Zimmer, L. S., Montgomery, D. C., & Runger, G. C. (2000). Guidelines for the application of adaptive control charting schemes. International Journal of Production Research, 38(9), 1977-1992.