跳到主要內容

臺灣博碩士論文加值系統

(44.211.31.134) 您好!臺灣時間:2024/07/22 19:24
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:吳思瑤
研究生(外文):Szu-Yao Wu
論文名稱: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
論文名稱(外文):Application of Statistical Features in Yarn Tension Pattern Recognition using Support Vector Machine and Artificial Neural Network
指導教授:鄭春生鄭春生引用關係
指導教授(外文):Chuen-Sheng Cheng
學位類別:碩士
校院名稱:元智大學
系所名稱:工業工程與管理學系
學門:工程學門
學類:工業工程學類
論文種類:學術論文
論文出版年:2008
畢業學年度:96
語文別:中文
論文頁數:78
中文關鍵詞:紗線張力非隨機樣式單變量管制圖相關係數統計特徵值支援向量機類神經網路
外文關鍵詞:yarn tensionunnatural patternscontrol chartcorrelation coefficientstatistical featuresupport vector machineartificial neural network
相關次數:
  • 被引用被引用:4
  • 點閱點閱:170
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在統計製程管制 (statistical process control, SPC) 中,管制圖是最常被應用的工具,可用來判斷製程中是否因存在可歸屬原因而造成製程的變異。製程中若存在可歸屬原因,管制圖上之統計量會超出管制上下界或呈現特定之非隨機性樣式,包括趨勢樣式、偏移樣式、週期樣式及混合樣式。然而在實際製程中,常出現各式各樣之非隨機樣式,無法以上述非隨機性樣式來歸類;因此,如何在眾多複雜的非隨機樣式中,正確對每種非隨機樣式作辨識,縮小診斷製程中可歸屬原因之範圍,將有助於規劃改善對策的施行與效益。

本研究之目的為以相關係數為基礎,發展出一系列自我比對的相關係數及使用其它有用之特徵值,對紗線之製程數據作轉換;再使用支援向量機與類神經網路,建構一個能對紗線張力非隨機性樣式作有效辨識與偵測之辨識系統,以作為實施製程規劃矯正措施及改善產品品質之重要依據。

研究顯示,原始數據經特徵值轉換後,在支援向量機與類神經網路對於非隨機樣式的辨識績效上,呈現較佳的辨識績效;兩種分類器之辨識能力亦相同。
Control chart pattern recognition is an important work in statistical process control. A control chart may present several unnatural patterns which including trends, sudden shifts, mixtures, and cyclic patterns. The occurrence of unnatural patterns implies that the process is affected by assignable causes, and corrective actions should be taken. Actually, the types of unnatural patterns which exist in real process are comprehensive. Identification correctly of unnatural patterns can greatly narrow the set of possible causes that must be investigated, and thus the diagnostic search time could be reduced in length.

The purpose of this research was to develop two classifiers based on support vector machine (SVM) and artificial neural network (ANN) to classify unnatural patterns in yarn tension data. First, we apply some statistical features to extract distinguished features from raw data. The extracted features are used as the components of the input vectors. Secondly, we develop SVM-based and ANN-based classifiers for control chart pattern recognition. The performances of two recognizers using statistical features extracted from correlation coefficient as the components of the input vectors was investigated and compared.

The results show that the SVM and ANN have similar recognition performances. Extensive comparisons indicate that the proposed recognizers perform better than that using raw data as inputs. Our research concluded that the extracted statistical features can reduce the input vectors while maintaining good levels of accuracy.
目錄
中文摘要 i
英文摘 ii
誌謝 iv
目錄 v
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 研究方法與步驟 4

第二章 文獻探討 6
2.1 傳統統計製程管制法 6
2.2 管制圖非隨機樣式之辨識 6
2.3 支援向量機偵測管制圖非隨機樣式之應用 9
2.4 類神經網路偵測管制圖非隨機樣式之應用 10
2.5 特徵值擷取於製程數據之應用 12

第三章 製程介紹 16
3.1 製程概論 16
3.2 監控與偵測系統 16
3.2.1 機器設備介紹 17
3.2.2 偵測原理及訊號紀錄 19
3.3 非隨機性樣式之種類與發生原因 21
3.4 紗線生產監控流程 30

第四章 研究方法 31
4.1 特徵值應用於資料之轉換 31
4.2 支援向量機之分類器 37
4.3 類神經網路之分類器 40

第五章 非隨機樣式之辨識系統 44
5.1 非隨機樣式數據之模擬 44
5.1.1 原始數據之模擬 44
5.1.2 特徵值之定義 49
5.2 支援向量機之架構 56
5.3 類神經網路之架構 57

第六章 效益評估 59
6.1 效益評估指標 59
6.2 辨識績效之評估 59
6.2.1 支援向量機之辨識績效 60
6.2.2 類神經網路之辨識績效 64
6.2.3 特徵值應用於非隨機樣式之判定準則 71

第七章 結論與未來研究 74
7.1 結論 74
7.2 未來研究 75

參考文獻 76


表目錄

表3.1 製程樣式發生原因對照表 29
表5.1 各樣式之參數設定 48
表5.2 學習樣本個數 49
表5.3 相關係數一之圖示與計算 52
表5.4 相關係數二之圖示與計算 52
表5.5 相關係數三之圖示與計算 52
表5.6 非隨機樣式之特徵圖形描繪與數值 53
表5.7 非隨機樣式之特徵圖形描繪與數值 (續一) 54
表5.8 非隨機樣式之特徵圖形描繪與數值 (續二) 55
表5.9 支援向量機輸入資料之參數設定 56
表5.10 類神經網路各樣式之輸出表達方式 58
表6.1 SVM 辨識結果 (數入訊號為原始數據,已正規化) 61
表6.2 SVM 辨識結果 (輸入訊號為特徵值,已正規化) 62
表6.3 SVM 平均辨識率 62
表6.4 SVM 辨識績效提升率 64
表6.5 ANN 辨識結果 (輸入訊號為原始數據) 65
表6.6 ANN 辨識結果 (輸入訊號為特徵值) 66
表6.7 ANN 平均辨識率 66
表6.8 ANN 辨識績效提升率 68
表6.9 SVM 去除常態之辨識結果 (輸入訊號為特徵值) 69
表6.10 ANN 去除常態之辨識結果 (輸入訊號為特徵值) 70
表6.11 SVM 與 ANN 平均辨識率 (去除常態,輸入向量為特徵值) 70


圖目錄

圖1.1 研究之架構流程圖 5
圖2.1 區間測試法 7
圖3.1 紗線生產之線上張力監視系統 18
圖3.2 傳感器 18
圖3.3 計算機系統操作平面圖 20
圖3.4 張力訊號圖 22
圖3.5 樣式一之張力訊號原始暨模擬圖 23
圖3.6 樣式二之張力訊號原始暨模擬圖 23
圖3.7 樣式三之張力訊號原始暨模擬圖 24
圖3.8 樣式四之張力訊號原始暨模擬圖 25
圖3.9 樣式五之張力訊號原始暨模擬圖 25
圖3.10 樣式六之張力訊號原始暨模擬圖 26
圖3.11 樣式七之張力訊號原始暨模擬圖 27
圖3.12 樣式八之張力訊號原始暨模擬圖 27
圖3.13 樣式九之張力訊號原始暨模擬圖 28
圖3.14 樣式十之張力訊號原始暨模擬圖 29
圖3.15 紗線生產監控流程圖 30
圖4.1 樣式四不同時間曲線圖之範例 32
圖4.2 樣式九不同時間曲線圖之範例 33
圖4.3 線性分割之圖例 38
圖4.4 非線性分割之圖例 38
圖4.5 高維度特徵空間轉換圖 39
圖4.6 倒傳遞網路之基本架構圖 41
參考文獻

1.Al-Ghanim, A. M. and Ludeman, L. C., “Automated unnatural pattern recognition on control charts using correlation analysis techniques,” Computers and Industrial Engineering, 32, 679-690 (1997).
2.Cheng, C. S., “A neural network approach for the analysis of control chart pattern,” International Journal of Production Research, 35, 667-697 (1997).
3.Cheng, C. S. and Chen, S. J., “Control chart pattern recognition using average of cumulative sum,” The Asian Journal on Quality, 1, 81-88 (2000).
4.Cheng, C. S. and Hubele, N. F., “A pattern recognition algorithm for an control chart,” IIE Transactions, 28, 215-224 (1996).
5.Cheng, C. S., and Tzeng, C. A., “A neural network approach for detecting shifts in the process mean and variability,” Journal of the Chinese Institute of Industrial Engineers, 11, 67-75 (1994).
6.Chinnam, R. B., “Support vector machines for recognizing shifts in correlated and other manufacturing processes,” International Journal of Production Research, 40, 4449-4466 (2002).
7.Crowder, S. V., “A simple method for studying run-length distributions of exponentially weighted moving average charts,” Technometrics, 29, 401-407 (1987).
8.Crowder, S. V., “Design of exponentially weighted moving average schemes,” Journal of Quality Technology, 24, 12-21 (1989).
9.Gao, Y., and Dooley, K. J., “Identification of change structure in statistical process control,” International Journal of Production Research, 30, 1655-1669 (1992).
10.Grant, E. L. and Leavenworth, R. S., Statistical Quality Control, McGraw-Hill Book Company., NY (1988).
11.Gauri, S. K. and Chakraborty, S., “Feature-based recognition of control chart patterns,” Computers and Industrial Engineering, 51, 726-742 (2006).
12.Gauri, S. K. and Chakraborty, S., “A study on the various features for effective control chart pattern recognition,” International Journal of Advanced Manufacturing Technology, 34, 385-398 (2007).
13.Hush, D. R., Salas, J., M., and Horne B. G., “Error surfaces for multi-layer perceptrons,” IEEE Transactions on System, Man and Cybernetrics, 22, 1152-1161 (1992).
14.Hwarng, H. B. and Hubele, N. F., “Back-propagation pattern recognizers for X-bar control chart: Methodology and Performance,” Computers and Industrial Engineering, 24, 219-235 (1993).
15.Hwarng, H. B. and Hubele, N. F., “ control chart pattern identification through efficient off-line neural network training,” IIE Transactions, 3, 25, 27-40 (1993).
16.Hassan, A., Baksh, M. S., Shaharoun, A. M. and Jamaluddin, H., “Improved SPC chart recognition using statistical features,” International Journal of Production Research, 41, 1587-1603 (2003).
17.Lucas, J. M., “Combined-Shewhart-CUSUM quality control schemes,” Journal of Quality Technology, 14. 51-59 (1982).
18.Lucas, J. M. and Saccucci, M. S., “Exponentially weighted moving average control schemes: properties and enhancements,” Technometrics, 32, 1-29 (1990).
19.Nelson, L. S., “The Shewhart control chart-test for special cause,” Journal of Quality Technology, 16, 237-239 (1984).
20.Nelson, L. S., “Interpreting Shewhart X-bar control charts,” Journal of Quality Technology, 17, 114-116 (1985).
21.NeuralWare Professional II/Plus. Neural Computing: A Technology Handbook for Professional II/Plus and NeuralWorks Explorer. Pittsburgh: NeuralWare, Inc (1997).
22.Page, E. S., “Continuous inspection schemes,” Biometrika, 41, 100-115 (1954).
23.Pham, D. T. and Wani, M. A., “Feature-based control chart pattern recognition,” International Journal of Production Research, 35, 1875-1890 (1997).
24.Roberts, S. W., “Properties of control chart zone tests,” Bell System Technical Journal, 37, 83-113 (1958).
25.Roberts, S. W., “Control chart tests based on geometric moving averages,” Technometrics, 1, 239-250 (1959).
26.Rodriguez, J. J., Alonso, C. J., and Maestro, J. A., “Support vector machines of interval-based features for time series classification,” Knowledge-Based Systems, 18, 171-178 (2005).
27.Statistica. Statistica Data Miner. OK: Stat Soft, Inc (2005).
28.Tan, P. N., Steinbach, M., and Kumar, V., Introduction to Data Mining, Addison-Wesley, Boston (2006).
29.Vapnik, V. N., Statistical Learning Theory, Wiley, New York (1998).
30.Western Electric Company, Statistical Quality Control Handbook, Western Electric Co. Inc., Indianapolis, Indiana (1958).
31.Yang, J.-H., and Yang, M.-S., “A control chart pattern recognition system using a statistical coefficient method,” Computers and Industrial Engineering, 48, 205-221 (2005).
32.羅宗元,「應用小波分析與類神經網路於管制圖非隨機樣式之偵測」,中壢,元智大學工業工程與管理研究所碩士論文 (2005)。
33黃啟原,「應用小波分析法與類神經網路建構管制圖非隨機樣式之辨識系統」,中壢,元智大學工業工程與管理研究所碩士論文 (2006)。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊