臺灣博碩士論文加值系統

在生產產品的製造過程中，如何快速的偵測到製程偏移，是監控製程中一項重要的研究議題。有效偵測製程偏移，能幫助製程監控人員迅速找到原因並且作改善製程。而現今同時監控數個品質特性已成趨勢，且當多項品質特性存在相關性，便會使用多變量管制圖做為主要的監控工具。MEWMA管制圖考慮了製程的歷史資料，在製程平均偏移量小幅度偏移的情形下，表現優於Hotelling’s T2管制圖，故選擇其統計量作為參考與比較。而在過去統計管制上，管制圖僅能偵測失控，無法給予監控人員更多偏移資訊，本研究利用神經網路的優異學習能力來建立監控模型，除了偵測製程偏移，亦能得到偏移的相關資訊。
在過去中的類神經網路僅能將二維資料以一維的方式輸入，本研究使用卷積神經網路，其能在二維資料做特徵擷取，故本研究將原始資料以及其多變量的統計距離結合作為二維輸入向量，透過深度學習網路方法建立偵測模型。監控過程分為兩階段，首先，先偵測製程是否偏移，再判斷其偏移資訊，偏移資訊包含何項品質特性偏移以及其分別的偏移量。並針對不同歷史權重的MEWMA資料不同分析視窗大小以及不同相關係數，利用平均連串長度(ARL)針對模型一以及準確率針對模型二進行績效評估。實驗結果顯示，同時將原始資料結合多變量的統計距離作成二維輸入向量，並且使用卷積神經網路去做特徵擷取，能比起過去統計製程管制以及機器學習方法能更有效偵測偏移，以及辨識偏移情境。

Detecting and identifying the mean shift in the manufacturing process has always been an important issue. An effective detection method can help engineers figure out the root causes of the shift so as to improve or restore the underlying manufacture process. If one has to monitor multiple quality characteristics simultaneously, the multivariate control chart can be used as an effective monitoring tool. The MEWMA control chart is one type of multivariate control chart, which considers previous data, and performs better than Hotelling’s T2 control chart when dealing with small shifts. Therefore, we take MEWMA statistics as our training feature. In addition, control charts can just detect the shift but can not tell more shift information. In this research, we have constructed a monitoring process that includes two models, both of which utilize neural networks, which are known for having excellent learning abilities. The monitoring process can not only detect the mean shift, but also provide us with the quantification of the shift.
In this study, we have decided to use convolution neural networks, which are able to extract the effective features in two-dimensional data. So we combine the raw data with MEWMA statistics as our input vector. There is a total of two phases in the monitoring process. Firstly, we work to detect the mean shift. If it is determined that a shift exists, we subsequently perform additional tests in acquire the shift quantification of each quality characteristic. We use ARL and accuracy to evaluate the first and the second model, then we perform a sensitivity analysis by appointing different MEWMA weights, window sizes, and correlation coefficients. Our results show that our way of combining raw data and MEWMA statistics as our training features, and by using CNN in extracting the features, is more effective compared to using SPC as well as the previous machine learning methods. The advantage also stands in the identification of extra information regarding the shift quantification.

摘要 i
英文摘要 ii
誌謝 x
表目錄 xiii
圖目錄 xiv
第一章 緒論 1
第一節 研究背景與動機 1
第二節 研究目的 3
第三節 研究範圍與限制 3
第四節 研究流程 5
第五節 論文架構 6
第二章 文獻探討 7
第一節 多變量統計管制法 7
第二節 偏移起始點 12
第三節 類神經網路 14
第四節 支援向量機 17
第五節 深度學習網路 20
第六節 小節 25
第三章 建構多變量製程監控模式 26
第一節 模式建構程序 26
第二節 訓練樣本產生過程 27
第三節 模型一架構 29
第四節 模型二架構 34
第五節 模型評估方式 36
第六節 小結 38
第四章 模式分析與驗證 39
第一節 情境說明 39
第二節 神經網路參數設定 40
第三節 模型一實驗結果及敏感度分析 43
第四節 模型二實驗結果及敏感度分析 50
第五節 小結 57
第五章 結論及建議 59
第一節 結論 59
第二節 未來研究建議與方向 60
參考文獻 62

Ahmadzadeh, F. (2009). Change point detection with multivariate control charts by artificial neural network. International Journal of Advanced Manufacturing Technology, 97(9-12), 3179-3190.
Ahmadzadeh, F. (2013). Multivariate process parameter change identification by neural network. International Journal of Advanced Manufacturing Technology, 69(9–12), 2261–2268
Atashgar, K. (2013). Identification of the change point: An overview. International Journal of Advanced Manufacturing Technology, 64(9–12), 1663–1683.
Ahmadzadeh, F. and Noorossana, R. (2008). Identifying the time of a step change with MEWMA control charts by articial neural network, The 8th International
Industrial Engineering and Engineering Management Conference, Singapore.
Atashgar, K. (2015). Monitoring multivariate environments using artificial neural network approach: An overview. Scientia Iranica, 22(6), 2527-2547.
Bersimis, S., Psarakis, S. and Panaretos, J. (2007). Multivariate statistical process control charts: An overview. Quality and Reliability Engineering International, 23(5), 517-543.
Chang, C. C. and Lin, C. J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3).
Chen, L. H. and Wang, T. Y. (2004). Artificial neural networks to classify mean shifts from multivariate chart signals. Computers ＆ Industrial Engineering, 47(2-3), 195-205.
Cheng, C. S. (1994). Detecting changes in the process mean using artificial neural networks approach. Journal of Chinese Institute of Industrial Engineers, 11, 47-54.
Cheng, C. S. (2011). Using neural networks to detect the bivariate process variance shifts pattern. Computers ＆ Industrial Engineering, 60(2), 269-278.
Convolution Introduction
https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/convolution.html(2018/11/18)
Crosier, R. B. (1988). Multivariate generalizations of cumulative sum quality control schemes. Technometrics, 30(3), 291-303.
Guh, R. S. (2006). On‐line Identification and Quantification of Mean Shifts in Bivariate Processes using a Neural Network‐based Approach. Quality and Reliability Engineering International,23(3),367-385.
Hinton, G. E., Osindero, S. and Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527-1554.
Hotelling, H. (1947). Multivariate quality control-illustrated by the air testing of sample bombsights. Techniques of Statistical Analysis, Eisenhart, C., Hastay, M. W. and Wallis, W. A., McGraw-Hill, New York, 11-184.
Hwarng, H. B. (2004). Detecting process mean shift in the presence of autocorrelation: a neural-network based monitoring scheme. International Journal of Production Research.42(3),573-595.
Nedumaran, G. (1998). Identifying the Time of a Step-Change with χ2 Control Charts. Quality Engineering, 13(2):765-778.
Niaki, S.T.A. and Abbasi, B. (2005).Fault diagnosis in multivariate control charts using articial neural network, Quality and Reliability Engineering International, 218,825-840.
Noorossana, R., Atashgar, K. and Saghaie, A. (2011). An integrated solution for monitoring process mean vector, International Journal of Advanced Manufacturing Technology, 56(5), 755-765.
Jian Z., Xia B., Wang C., Li Z. (2019). Diagnosis of Out-of-Control Signals in Multivariate Manufacturing Processes with Random Forests, Advanced Manufacturing and Automation VIII. IWAMA 2018. Lecture Notes in Electrical Engineering, 484, 262-267.
Karacapilidis, N., Fountoulaki, A. (2011). Using neural networks for mean shift identification and magnitude of bivariate autocorrelated processes.  International Journal of Quality Engineering and Technology, 2(2), 114-128.
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86 (11): 2278-2324.
Lowry, C. A., Woodall, W. H., Champ, C. W. and Rigdon, S. E. (1992). A multivariate exponentially weight moving average control chart. Technometrics, 34(1), 46-53.
Lowry, C. A. and Montgomery, D. C. (1995). A review of multivariate control charts. IIE Transactions, 27(6), 800-810.
Prabhu, S. (1997). Designing a Multivariate EWMA Control Chart, Journal of
Quality Technology, 29(1): 8-15.
Pugh, G. A. (1991). A comparison of neural networks to SPC charts. Computers ＆ Industrial Engineering. 21(1-4), 1991, 253-255.
ReLU function
https://zh.wikipedia.org/wiki/%E7%BA%BF%E6%80%A7%E6%95%B4%E6%B5%81%E5%87%BD%E6%95%B0
Roberts, S. W. (1959). Control chart test based on Geometric Moving Averages,
Technometrics, 42(1), 97-101.
Salehi, M., Kazemzadeh, R. B. and Salmasnia, A. (2012). On line detection of mean and variance shift using neural networks and support vector machine in multivariate processes. Applied Soft Computing, 12(9), 2973-2984.
Win, B. and Yu, J. B. (2010). A neural network ensemble model for on-line monitoring of process mean and variance shifts in correlated processes. Expert Systems with Applications, 37(6), 4058-4065.
Wang, T. Y. and Chen, L. H. (2002). Mean shifts detection and classification in
multivariate process: a neural-fuzzy approach. Journal of Intelligent Manufacturing, 13(3), 211-221.
Yu, J.B., Xi, L.F. and Zhou, X. (2009). Identifying source(s) of out-of-controlling signal in multivariate manufacturing process using selective neural network ensemble, Engineering Applications of Articial Intelligence, 22, 141-152.
Zheng, X. Y. and Yu, J. B. (2019). Multivariate process monitoring and fault identification using convolutional neural networks. Proceeding of the 24th International Conference on Industrial Engineering and Engineering Management 197-208.