臺灣博碩士論文加值系統

現今的產業的生產方式，產品之間的資料往往存在著自我相關的情形，有鑑於此，本研究之主要目的是利用決策樹可以快速分類的特性，來建立一個同時考慮多個品質特性且產品彼此之間具有相關性的製程辨識系統，作為修正或改善產品的品質之依據。本研究利用決策樹針對多變量自我相關製程之非隨機樣式來進行監控，並採用多變量自我迴歸 (Vector Autoregressive, VAR)模式來模擬多變量自我相關製程，搭配不同的非隨機樣式和相關性進行監控。研究結果發現，在兩個變量為正相關下，辦識率受自我相關程度之影響較大，而在兩個變量為正或負相關下且僅出現一個非隨機樣式時，辦識率受自我相關程度之影響的程度較小。在相關係數ρ方面則是當兩變量為正相關時，單一變量發生非隨機樣式，辨識率會隨著ρ呈現遞增之趨勢，兩變量發生非隨機樣式，則辨識率會隨著ρ呈現遞減之趨勢；而當兩變量為負相關時，不管單一或兩變量發生非隨機樣式，其辨識率皆會隨著負相關程度而增加。

There have processes which have multiple quality characteristics and the data is autocorrelated in practice. This research uses the decision tree to develop a nonrandom patterns recognition system to monitor the multivariate autocorrelated processes. The results show that if variables are positively correlated, the correct identification rate will be influence by the degree of autocorrelation. As regarding of correlation coefficient, when variables are positively correlated, the correct identification rate will increase as ρ increase if only single variable has assignable causes variation; however, if both variables have assignable causes variation, the correct identification rate will decrease as ρ increase. When two variables are negatively correlated, the correct identification rate will increase as ρ increase regardless of single or two variables have assignable causes variation.

摘要 iii
ABSTRACT iv
誌謝 v
目錄 vi
表目錄 viii
圖目錄 ix
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 研究範圍 3
1.4 研究論文內容 3
第二章 文獻探討 4
2.1 製程管制 4
2.1.1 傳統製程管制 5
2.1.2 多變量製程管制 7
2.2自相關製程 9
2.3 管制圖之非隨機樣式 10
2.3.1 單變量之非隨機樣式 11
2.3.2 多變量之非隨機樣式 14
2.4決策樹之理論 17
2.5 蒙地卡羅模擬法 20
2.6 特徵值之擷取 22
第三章 研究方法 23
3.1 研究方法流程 23
3.2 多變量統計製程管制 24
3.3決策樹 26
3.4樣本的產生 28
3.4.1向量自我迴歸模型 28
3.4.2 自相關製程中管制圖非隨機樣式 29
3.5製程特徵值 32
3.6績效評估 35
第四章 模擬結果與分析 36
4.1實驗步驟 36
4.2 數據分析 37
4.2.1兩個變量為正相關 37
4.2.1.1僅出現一個非隨機樣式 37
4.2.1.2皆出現非隨機樣式 39
4.2.2兩個變量為負相關 41
4.2.2.1僅出現一個非隨機樣式 41
4.2.2.1皆出現非隨機樣式 43
4.2.3自我相關程度對分類準確率之影響 44
第五章 結論與未來發展 45
5.1 總結 45
5.2未來發展方向 46
參考文獻 47

邱玉琳，2007，應用類神經網路與支援向量機於多變量自我相關製程變異來源之辨識，元智大學工業工程與管理研究所，碩士論文。
張云濤、龔玲，2007，資料探勘原理與技術，五南圖書有限公司，台北。
張正賢，1997，統計品質管制，第二版，華泰書局，台北。
張秉宸，2007，應用類神經網路與支援向量機建構多變量管制圖非隨機樣式之辨識系統，元智大學工業工程與管理研究所，碩士論文。
黎科麟，2009，應用支撐向量機於多變量自我相關製程之探討，國立雲林科技大學工業工程與管理所，碩士論文
Arkat, J , Niaki, S T A ,and Abbasi, B ,2007, “Artificial neural networks in applying MCUSUMresiduals charts for AR(1) processes” , Applied Mathematics and Computation, Vol.189, pp.1889–1901.
Charnes, J M., 1995, “Tests for special causes with multivariate autocorrelated data”, Computers Ops Res, Vol. 22, pp.443-453, ()
Gauri, S. K. and Chakraborty, S., 2006, “Feature-based recognition of control chart patterns”, Computers & Industrial Engineering, Vol.51, pp.726–742.
Gauri, S.K. and Chakraborty, S.,2007, “A study on the various features for effective control chart pattern recognition”, International Journal of Advanced Manufacturing Technology, Vol 34(3-4), pp385-398
Grant,E.L and Leavenworth,R.S,1996, “Statical Quality Control,7thed,McGraw Hill”,PP386-391.
Guh, R.S and Shiue, Y.R., 2008, “An effective application of decision tree learning for on-line detection of mean shifts in multivariate control charts”, Computers & Industrial Engineering, Vol.55, pp.475–493.
Issam, B.K and Mohamed, L., 2008, “Support vector regression based residual MCUSUM control chart for autocorrelated process”, Applied Mathematics and Computation, Vol.201, pp.565–574.
Jarretta, E.E. and Pan, X., 2007, “The quality control chart for monitoring multivariate autocorrelated processes”, Computational Statistics & Data Analysis , Vol.51, pp.3862–3870.
Kalgonda, A. A. and Kulkarni, S. R., 2004, “Multivariate Quality Control Chart for Autocorrelated Processes”, Journal of Applied Statistics, Vol. Vol.31, pp.317–327.
MacGregor, J.F. and Kourtl, T., 1995, “Statistical Process Control Of Multivariate Processes”, Control Fag. Practice, Vol.3, pp.403-414.
Mason, R. L., Chou, Y. M., Sullivan, J. H., Stoumbos, Z. G., and Young, J. C., 2003, “Systematic patterns in T 2 charts”,Journal of Quality Technology, Vol. 35, pp.47-58.
Montgomery, D. C., 2001, Introduction to Statistical Quality Control, Wiley, New York.
Nelson, L. S., 1984, “The Shewhart control chart-tests for special cause” , Journal of Quality Technology, Vol 16- 4, pp.237-239
Pal, M. and Mather, P.M., 2003, “An assessment of the effectiveness of decision tree methods for land cover classification”, Remote Sensing of Environment , Vol.86, pp.554–565.
Pandya, A. S. and Macy, R. B. 1996, Pattern Recognition with Neural Network in C ++, CRC, Florida.
Wang, C.H, GUO, R.S, Chiang, M.H, and Wong, J.Y, 2007, “International Journal of Production Research”,pp.1–13.
WANG, K. and TSUNG, F, 2007, “Monitoring feedback-controlled processes using adaptive T^2 schemes”, International Journal of Production Research, Vol. 45, pp.5601–5619.
Wang, Z. and Ong, K.C.G., 2008, “Autoregressive coefficients based Hotelling’sT^2 control chart for structural health monitoring”, Computers and Structures, Vol.86, pp.1918–1935.
Western Electric Company, 1958, Statistical Quality Control Handbook, Western Electric Co Inc, Induana.