臺灣博碩士論文加值系統

統計製程管制 (statistical process control, SPC) 是以統計手法針對製程進行監控、分析與改善，所以是屬事前預防。其主要是監控製程是否存在可歸屬原因 (assignable causes) 所導致之變異，以提早採取製程改善之行動，避免增加產品額外的生產成本。而在統計製程管制方法中管制圖 (control chart) 是最常被應用之重要工具，它可以用來決定系統的狀態並偵測製程中隨時可能發生的異常情況。異常的管制圖形狀與製程變異中一些特殊的非機遇性原因有關聯，因此有效地辨識異常管制圖形狀能減少可能需要的檢查次數，並加速診斷搜尋，所以這是屬於一種分類問題。而類神經網路 (artificial neural network) 與支援向量機 (support vector machine) 被廣泛的應用在分類問題上，並有許多研究指出具有良好的效益，因此本研究擬應用類神經網路與支援向量機做為線上偵測製程之監控系統，並利用蒙地卡羅模擬法產生出生產線製程數據並結合由製程數據所擷取出的統計特徵值當作此兩種工具的訓練範例與測試範例，並做其比較。本論文同時討論在常態環境下利用標準差代替系統或生產線上的雜訊值，所以利用不同標準差做動態測試的動作，並比較其績效。結果顯示，支援向量機的整體平均辨識率為 91% 優於類神經網路的整體平均辨識率 83%；支援向量機的整體平均連串長度為 6.5 優於類神經網路的整體平均連串長度 6.8；支援向量機的整體連串長度標準差為 1.8 優於類神經網路的整體連串長度標準差2.1。由結果證明，支援向量機在對於線上辨識異常管制圖的整體績效或者雜訊容忍程度是優於類神經網路的。

Statistical process control is a method of statistic to be aimed at manufacturing to proceed monitor, analysis and improve. So it is belong to preventing in advance. It can detect assignable cause during the process control which may occur and provide help to improve process and reduce unnecessary product cost. Hence, control chart is an important tool at statistical process control. Control charts can detect abnormal status during the process control which may occur at any time. Unnatural CCPs can be associated with a particular set of assignable causes for process variation. Essentially, the judgement of the process states can be seen as a classification problem in artificial intelligence. Artificial neural network (ANN) and support vector machine (SVM) generally were used in classification pattern, and a lot of researches were pointed out that ANN and SVM have excellent performances. So in this research is using ANN and SVM in on-line manufacturing control system. The training data set and testing data set were used in which hybrid training data were generated by Monte-Carlo Simulation Method for production line process data. At the same times to discuss under the normal environment to make use of standard deviation to replace system or production line’s noise, so make use of the action , that the different standard deviation does a dynamic state test and compare its results. The result showed that SVM’s overall average recognition rate is 91% surpass ANN’s overall average recognition rate 83% ; SVM’s overall average run length is 6.5 surpass ANN’s overall average run length 6.8 ; SVM’s overall sigma of run length is 1.8 surpass ANN’s overall sigma of run length 2.1 . Proved by the result that SVM’s overall performance or the noise tolerant of degree surpass ANN’s.

中文摘要 --------------------------------------------- i
英文摘要 --------------------------------------------- ii
誌謝 --------------------------------------------- iii
目錄 --------------------------------------------- iv
表目錄 --------------------------------------------- vii
圖目錄 --------------------------------------------- viii
符號說明 --------------------------------------------- xi
第一章 緒論----------------------------------------- 1
1.1. 研究背景與動機------------------------------- 1
1.2. 研究目的------------------------------------- 3
1.3. 研究範圍------------------------------------- 4
1.4. 研究假設------------------------------------- 5
1.5. 研究方法與流程------------------------------- 6
1.6. 論文架構------------------------------------- 10
第二章 文獻探討------------------------------------- 12
2.1. 傳統製程管制方法之相關文獻------------------- 12
2.2. 辨識非隨機性模型之相關文獻------------------- 15
2.3. 應用類神經網路於製程非隨機形狀辨識之相關文獻- 16
2.4. 應用支援向量機之相關文獻--------------------- 20
2.5. 擷取特徵值之相關文獻------------------------- 26
第三章 管制圖非隨機形狀----------------------------- 28
3.1. 管制圖非隨機形狀之種類----------------------- 28
3.2. 製程數據收集--------------------------------- 32
3.3. 數據之模擬----------------------------------- 33
3.3.1. 模擬的定義與程序----------------------------- 33
3.3.2. 蒙地卡羅模擬法的基本理論架構----------------- 35
3.4. 管制圖非隨機形狀之數學式--------------------- 36
3.5. 製程中非隨機形狀辨識程序所具備之條件--------- 38
第四章 類神經網路----------------------------------- 40
4.1. 類神經之發展過程----------------------------- 40
4.2. 類神經網路之基本原理------------------------- 42
4.3. 類神經網路組成要素--------------------------- 45
4.4. 類神經網路之特性與應用----------------------- 48
4.5. 倒傳遞網路----------------------------------- 50
4.6. 倒傳遞網路之學習演算法----------------------- 53
4.7. 倒傳遞類神經網路之參數設定------------------- 56
第五章 支援向量機----------------------------------- 59
5.1. 支援向量機之發展介紹------------------------- 59
5.2. 支援向量機簡介------------------------------- 59
5.3. 支援向量機的種類----------------------------- 62
5.4. 支援向量機之優點----------------------------- 69
5.5. 支援向量機之應用----------------------------- 69
第六章 統計特徵值----------------------------------- 72
6.1. 平均值--------------------------------------- 72
6.2. 標準差--------------------------------------- 72
6.3. 偏態係數------------------------------------- 73
6.4. 峰態係數------------------------------------- 73
6.5. 斜率----------------------------------------- 74
6.6. 皮爾森相關係數------------------------------- 74
第七章 辨識管制圖非隨機形狀之類神經網路------------- 75
7.1. 分析視窗------------------------------------- 75
7.2. 網路架構------------------------------------- 76
7.3. 產生訓練樣本--------------------------------- 80
7.4. 類神經網路模型之訓練------------------------- 81
7.5. 類神經網路模型之測試------------------------- 82
7.6. 衡量指標------------------------------------- 83
第八章 辨識管制圖非隨機形狀之支援向量機------------- 84
8.1. 研究架構------------------------------------- 84
8.2. 分析視窗------------------------------------- 88
8.3. 支援向量機之輸入卅輸出向量與訓練樣本之產生--- 88
8.4. 支援向量機之訓練----------------------------- 90
8.5. 支援向量機之測試----------------------------- 91
8.6. 衡量指標------------------------------------- 92
第九章 系統績效評估設定----------------------------- 93
9.1. 評估指標------------------------------------- 93
9.2. 類神經網路之評估程序------------------------- 93
9.3. 支援向量機之評估程序------------------------- 95
9.4. 動態測試與相關參數設定----------------------- 96
9.4.1. 類神經網路之動態測試相關參數設定------------- 97
9.4.2. 支援向量機之動態測試相關參數設定------------- 99
第十章 測試結果與分析------------------------------- 102
10.1. 類神經網路動態測試結果----------------------- 102
10.2. 支援向量機動態測試結果----------------------- 117
10.3. 類神經網路與支援向量機之績效評估與比較------- 132
第十一章 結論與未來展望------------------------------- 152
11.1. 結論----------------------------------------- 152
11.2. 貢獻----------------------------------------- 154
參考文獻 貢獻----------------------------------------- 156

1.王仁達 (1988)，應用類神經網路偵測製程平均值變化：設計策略之研究，元智大學，碩士論文。
2.王景南 (2003)，多類支援向量機，元智大學資訊管理研究所，碩士論文。
3.杜榮原 (2008)，以因子實驗法發掘支援向量機的重要變數與建構最小成本之診斷模型，中華大學資訊管理研究所，碩士論文。
4.李育昇 (2005)，支援向量機器於可靠度系統之應用，大葉大學工業工程研究所，碩士論文。
5.吳思瑤 (2008)，應用統計特徵值以支援向量機與類神經網路建構紗線張力非隨機樣式之辨識系統，元智大學工業工程研究所，碩士論文。
6.房克成與林清風 (2004)，管制圖與製程管制，中華民國品質學會，台北。
7.林裕章 (1992)，類神經網路應用於統計製程管制分隨機性模型之研判，元智大學工業工程研究所，碩士論文。
8.林榮合 (1999)，類神經網路於管制圖非隨機性模型辨識，元智大學工業工程研究所，碩士論文。
9.邱群穎 (2007)，應用支援向量機於監控相關性製程之研究，輔仁大學管理學研究所，碩士論文。
10.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，元智大學工業工程研究所，碩士論文。
11.阮冰如 (2006)，應用類神經網路與支援向量機於多變量製程變異來源之辨識，元智大學工業工程研究所，碩士論文。
12.阮清俊 (2008)，線上直堆式支援向量機，大葉大學電機工程研究所，碩士論文。
13.段建帆 (2005)，支援向量機之最佳化參數與屬性篩選之分散式資料探勘系統—以粒子群最佳化演算法為基礎，華梵大學資訊管理研究所，碩士論文。
14.施炳光（2007），結合製程統計特徵值與類神經網路於管制圖異常形狀之辨識，虎尾科技大學工業工程與管理研究所，碩士論文。
15.郭琇靜 (2008)，應用支援向量機與製程統計特徵於線上偵測製程異常之研究，虎尾科技大學工業工程與管理所，碩士論文。
16.許晉嘉 (2006)，應用支援向量機於高解析度衛星影像分類之研究，逢甲大學環境資訊科技所，碩士論文。
17.黃仁鋒 (2006)，模擬退火法應用於支援向量機之參數調整與屬性篩選，華梵大學資訊管理研究所，碩士論文。
18.黃志雄 (2007)，利用自動學習與錯誤過濾方法的多類別支援向量機分類系統，國立中正大學資訊工程研究所，碩士論文。
19.黃聖蕙 (1997)，模糊理論與類神經網路應用於管制圖之研究，元智工業工程研究所碩士論文。
20.曾慶安 (1994)，類神經網路在品質管制上的應用：以倒傳遞網路偵測製程個別數據之平均值及變異數的變化，元智大學工業工程研究所，碩士論文。
21.楊其龍 (1997)，應用類神經網路於相關性數據之製程管制法研究，大葉工學院，碩士論文。
22.楊超然 (1990)，作業研究，七版，三民書局發行，台北。
23.葉怡成 (1993)，類神經網路－模式應用與實作，儒林圖書有限公司。
24.葉怡成 (1995)，｢類神經網路在化工與化學上之應用｣，化工，42卷，2期，頁74-83。
25.管中閔 (2000)，統計學關觀念與方法，華泰文化事業股份有限公司，台北。
26.蔡依玲 (2001)，台灣股票市場報酬率之研究，國立成功大學統計研究所，碩士論文。
27.蔡政良 (1996)，以特徵為基之管制圖非隨機性模型辨認－使用類神經網路，元智大學工業工程研究所，碩士論文。
28.謝昆霖 (1995)，類神經網路在品質管制上之應用：非隨機性變化之偵測，元智大學工業工程研究所，碩士論文。
29.謝素妮 (2008)，應用支援向量機於偵測加入連串規則的Hotelling’s T2管制圖之平均值偏移，國立成功大學工業與資訊管理研究所，碩士論文。
30.魏宛茹 (2007)，資料前處理對於支援向量機之影響-以期貨預測為例，暨南國際大學資訊管理研究所，碩士論文。
31.顧瑞祥 (2003)，｢應用基因演算法最佳化偵測製程異常之類神經網路｣，中華民國品質學會第39屆年會暨第九屆全國品質研討會。
32.顧瑞祥和薛友仁 (2004)，｢應用資料採礦技術線上即時辨識管制圖之異常形狀｣。
33.顧瑞祥和薛友仁 (2004)，｢應用動態學習之神經網路偵測與分析管制圖之異常形狀｣，中華民國品質學會第40屆年會 (高雄市分會第30屆年會) 暨第十屆全國品質管理研討會論文集，A1-7，頁66-76。
34.Beneke, M., Leemis, L. M., Schlegel, E. E., & Foote, B. L. (1988). “Spectral analysis inquality control：a control chart based on the peridogram”, Technomertrics, vol 30, pp. 63-70.
35.Berry, M. J. A., & Linoff, G. (1997). Data Mining Technique for Marketing, Sale, and Customer Support. Wiley Computer, New York.
36.Borror, C. M., Montgomery, D. C., & Runger, G. C. (1999). “Robustness of the EWMA control chart to non-normality”, Journal of Quality Technology, vol. 31, no. 3, pp. 309-316.
37.Boser, B. E., Guyon, I. M., & Vapnik, V. (1992). A training algorithm for optimal margin classi_ers. In Fifth Annual ACM Workshop on Computational Learning Theory, pp. 144-152.
38.Brown, M., Grundy, W., Lin, D., Cristianini, N., Sugnet, C., Furey, T., Ares, M., & Haussler (1999). “Knowledge-base analysis of microarray gene expression data using support vector machine”, Technical report, University of California in Santa Cruz.
39.Burbudge, R., Trotter, M., Buxton, B., & Holden, S. (2001). “Drug design by machine learning：Support vector machine for pharmaceutical data analysis”, Computer and Chemistry, pp 5-14.
40.Burges, C. J. C. (1998). “A tutorial on support vector machines for pattern recognition”, Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 955-974.
41.Burr, I. W. (1953). Engineering Statistics and Quality Control, M-Hill.
42.Cabena, P., Hadinaian, P. O., Standler, D. R. J., Verhees, J., & Zannasi, A. (1998). Discovering Data Mining form Concept to Implementation, Prentice Hall.
43.Cao, L., & Gu, Q. (2002). “Dynamic support vector machines for non-stationary time series forecasting”, Intelligent data Analysis, vol. 6, pp. 67-83.
44.Champ, J. W., & Woodall, W. H. (1987). “Exact rusults for shewhat control charts with Supplementary Run Rules”, Technomertrics, vol. 29, pp. 393-399.
45.Cheng, C. S., & Tzeng, C. A. (1994). “A neural network approach for detecting shifts in the process mean and variability”, Journal of the Chinese Institute of Industrial Engineers, vol. 11, no. 2, pp. 67-75.
46.Cheng, C. S. (1995). “A multi-layer neural network model for detecting changes in the process mean ”, Computer & Industrial Engineering, vol. 28, no. 1, pp. 51-61.
47.Cheng, C. S. (1989). “Group technology and expert systems concepts applied to statistical process control in small-batch manufacturing”, Ph.D. Dissertation, Arizona State University, Tempe, AZ.
48.Cheng, C. S. (1997). “Neural network approach for the analysis of control chart patterns”, International Journal of Production Research, vol. 35,no. 3, pp. 667-697.
49.Chinnam, R. B. (2002). “Support vector machines for recognizing shift in correlated and other manufacturing process”, International Journal of Production Research, vol. 40, pp. 4449-4466.
50.Chiu, C. C., Chen, M. K., & Lee, K. M. (2001). “Shift recognition in correlated process data using a neural network”, International Journal of Systems Science, vol. 32, pp. 137-143.
51.Cho, S. B., & Won, H. H. (2003). “Machine Learning in DNA Microarray Analysis for Cancer Classification”, Asia-Pacific Bioinformatics Conference in Information Technology.
52.Cook, D. F., & Chiu, C. C. (1998). “Using radial basis function neural networks to recognize shift in correlated manufacturing process parameters”, IIE Transaction, vol. 30, pp. 227-234.
53.Cortes, C., & Vapnik, V. (1995). “Support vector networks”, Machine Learning, vol. 20, pp. 273-297.
54.Davis, R. B., & Woodall, W. H. (1988). “Performance of the control chart trend rule under linear drift”, Journal of Quality Technology, vol. 20, pp. 260-262.
55.Duncan, A. J. (1974). Quality Control and Industrial Statistical, 4, Richard D, Irwin Inc.
56.Fayyad, U., Piatetsky–Shapiro, G., & Smyth, P. (1996). “The KDD Process for Extracting Useful Knowledge form Volumes of Data”, Communications of the ACM, vol. 39, pp. 27-34.
57.Fletcher, R. (1987). Practical Methods of Optimization, John Wiley and Sons, Inc., 2nd edition.
58.Grant, E. L., & Leavenworth, R. S. (1988). Statistical Quality Control, McGraw-Hill, New York.
59.Grupe, F. H., & Owrang, M. M. (1995). “Database Mining Discovering New Knowledge and Cooperative Advantage”, Information Systems Management, vol. 12, pp. 26-31.
60.Guh, R. S., & Hsieh, Y. C.. (1999). “Aneural network based model for abnormal pattern recognition of control chart”, Computers & Industrial Engineering, vol. 36, pp. 97-108.
61.Guh, R. S., and Tannock, J. D. T. (1999). “Recognition of control chart concurrent patterns using a neural network approach”, International Journal of Production Research, vol. 37, pp. 1743-1765.
62.Guh, R. S. (2002). “Robustness of the neural network based control chart pattern recognition system to non-normality”, International Journal of Quality and Reliability Management, vol. 19, no. 1, pp. 97-112.
63.Guh, R. S. (2003). “Integrating artifical intelligence into on-line statistical processcontrol”, Quality and Reliability Engineering International, vol. 1,no. 1, pp. 1-20.
64.Guh, R. S. (2005). “A hybrid learning-based model for on-line detection and analysis of control chart patterns”, Computer & Industrial Engineering, vol. 49, pp. 35-62.
65.Guo, y., & Dooley k. J. (1992). “Indentification of change structure in statistical process control”, International Journal of Production Research, vol. 30, no. 2, pp. 1655-1669.
66.Ham, F. M., & Kostanic, I. (2001). Principles of Neurocomputing for Science & Engineering, McGraw-Hill, New York.
67.Hassan, A., et al. (2003). “Improved SPC chart pattern recognition using statistical features”, International Journal of Production Research, vol. 41, 7, pp. 1587-1603.
68.Hebb, D. O. (1949). The Organization of Behcaviour, Wiley, New York.
69.Hopfield, J. J. (1982). “Neural Networks and Physical Systems with Emergent Collective Computational Abilities”, Proceeding of the National Academy of Scientists, Vol. 79, pp. 2554-2558.
70.Hush, D. R., & Horne, B. G. (1993). “Progress in supervised neural network”, IEEE Signal Processing Magazine, pp. 8-39.
71.Hwarng, H. B., & Hubele, N. F. (1993). “Back-propagation pattern recognizers for X-bar control chart : Methodology and Performance”,Computers and Industrial Engineering, vol. 24, pp. 219-235.
72.Hwarng, H. B., & Hubele, N. F. (1993). ” control chart pattern identification through efficient off-line neural network training”, IIE Transactions, vol. 25, pp. 27-40.
73.Hwarng, H. B., & Chong, C. W. (1994). “Detecting process non-randomness through a fast and cumlative learning ART-based pattern recognizer”, International Journal of Prduction Research, vol. 33, no. 7, pp. 1817-1833.
74.Kuperstein, M., & Rubinstein, J. (1989). “Implementation of An Adaptive Neural Controller for Sensory-Motor Coordination”, UCNN 89 Proceeding, vol. 2, pp. 305-310.
75.Lavangnananda, K., & Nakkathon, A. (2003). “Improving Features Extraction in Control Chart Patterns”, Proceedings of the 7th National Computer Science and Engineering Conference, Thailand, pp. 364-369.
76.Lavangnananda, K., & Piyatumrong, A. (2005). “Image processing approach to features extraction in classification of control chart patterns”, Proceedings of the 2005 IEEE Mid-Summer Workshop on Soft Computing in Industrial Applications, Helsinki, pp. 85-89.
77.McClelland, T. L., & Rumelhart, D. E. (1986). Parallel Distributed Processing, Cambridge, MIT Press and the PDP Research Group.
78.McCulloch, W. S., & Pitts, W. H. (1943). “A Logical Calculus of the Ideals Immanent in Nervous Activity”, Bulletin of Mathematical Biophysics, pp. 115-133.
79.Minsky, M., & Papert, S. A. (1969). Perceptrons, Cambridge, MIT Press, MA.
80.Montgomery, D. C. (2005). Introduction to Statistical Quality Control. Wily, New York.
81.Nelson. L. S. (1984). “The Shewhat control chart-tests for special cause”, Journal of Quality Technology, vol.16, no. 4, pp.237-239.
82.Nelson. L. S. (1985). “Interpreting Shewhart X-bar control charts”, Journal of Quality Technology, vol.17, pp.114-116.
83.Pandya, A. S., & Macy, R. B. (1996). Pattern Recognition with Neural Network in C ++, CRC, Florida.
84.Pai, P. F., & Lin, C. S. (2004). “Using support vector machines in forecasting production value of machinery industry in Taiwan”, accepted by the International Journal of Advanced Manufacturing Technology.
85.Pham, D. T., & Oztemel, E. (1992). “Control chart pattern recognition using neural networks”, Journal of Systems Engineering, vol. 2, no. 4, pp. 256-262.
86.Pham, D. T., & Oztemel, E. (1994). “Control chart pattern recogition using learning vector quantization networks”, International Journal of Production Research, vol. 32, pp. 721-729.
87.Psaltis, D., Sideris, A., & Yamamura, A. (1987). “Neural Controllers In Proc”, IEEE Int Neural Networks Conf, San Diego, California, pp. 551-558.
88.Pugh, G. A. (1989). “Synthetic neural network for process control”, Computer and Industrial Engineering, vol. 17, pp. 24-26.
89.Pugh, G. A. (1991). “A comparison of neural networks to SPC chart”, Computer and Industrial Engineering, vol. 21, pp. 253-255.
90.Ribeiro, B. (2005). “Support vector machines for quality monitoring in a plasticinjection molding process”, IEEE Transactions on System, Man, & Cybernetics-Part, C.：Applications & Reviews, vol. 35, pp. 401-410.
91.Robert, S. W. (1958). “Properties of control chart zone test”, Bell System Technical Journal, vol. 37, pp. 83-113.
92.Rosenblatt, F. (1958). “The perceptron: A Probabilistic Model for Information Storage and Organization in the Brain”, Rev, Phych, pp. 86-408.
93.Sahrmann, H. (1979). “Set-up assurance through time series analysis”, Journal of Quality Technology, vol. 11, pp. 105-115.
94.Schilling, E. G., & Nelson, P. R. (1976). “The effect of non-normality on the control limits of X-bar charts”, Journal of Quality Technology, vol. 8, no. 4, pp. 183-188.
95.Scholkopf, B., & Smola, A. J. (2000). Statistical learning and kernel methods.Cambridge, USA.
96.Spedding, T. A., & Rawlings, P. C. (1994). “Non-normality in statistical process control measurements”, International Journal of Quality and Reliability Management, vol. 11, no. 6, pp. 27-37.
97.Spurruer, J. D., & Thombs, L. A. (1990). “Control chart for detecting cyclical behavior”, Technomertrics, vol. 32, pp. 163-171.
98.Sun, R., Tsung, F. (2003). “A kernel-distance-based multivariate control chart using support vector methods”, International Journal of Production Research, vol. 41, pp. 2975-2989.
99.Swift, J. A. (1987). “Development of a knowledge based expert system for control chart pattern recognition and snalysis”, The Oklahoma State, December.
100.Tay, F. E. H., & Cao, L. J. (2002). “Modified support vector machines in financial time series forecasting”, Neurocoputing, vol. 48, pp. 847-861.
101.Tontini, G. (1998). “Robust learning and identification of patterns in statistical process control charts using a hybrid RBF fuzzy artificial neural network”, IEEE International Joint Conference on Neural Network Proceedings, vol. 3, pp. 1694–1699.
102.Utku, H. (2000). “Application of the feature selection method to discriminatedigitised wheat varieties”, Journal of Food Engineering, vol. 46, pp. 211–216.
103.Vapnik, V. (1995). The Nature of Statistical Learning Theory. Springer Verlag ( ed.).
104.Wetherill, G. B., & Rrown, D. W. (1991). Statistical Process Control：Theory and Practice, Chapman and Hall, London.
105.Western Electric Company (1958), Statistical Quality Control Handbook, Indiana: Western Electric Co. Inc, Indianapolis.
106.Widrow, B., & Hoff, M. E. (1960). Adatpive Sitching Circuits, IRE Western Electric Show and Convention Record, pp. 96-104.
107.Yourstone, S. A., & Zimmer, W. J. (1992). “Non-normality and the design of control charts for averages”, Decision Sciences, vol. 23, pp. 1099-1113.
108.Zeki, A. A., & Zakaria, M. S. (2000). “New primitive to reduce the effect of noise for handwritten features extraction”, IEEE Intelligent Systems and Technologies for the New Millennium Proceedings, Tencon.
109.Zorriassatine, F., & Tannock, J. D. T. (1998). “A review of neural networks for statistical process control”, Journal of Intelligent Manufacturing, vol. 9, pp.209–224.