臺灣博碩士論文加值系統

本論文旨在建立一套光電檢測基重系統，此技術開發以非接觸、線上、多點區域、穿透式與驗證之技術，藉以改善量測不織布準確性和製程能力精密度。基本上，不織布基重系統由光源發射器穿透不織布，光傳輸平行於光接收器，利用比爾-朗伯定律，經訊號轉換輸出入介面裝置。
我們首先架設並進行光電檢測系統調整補償，實驗結果顯示經溫度補償後之系統相當穩定，再利用最小平方法找到一可靠有效的電壓值與基重之參數關係方程式，經使用已知不織布基重之量測，結果顯示所量測獲得之基重值與已知值相符。找出適合電壓、基重參數關係方程式，藉由選取三種原料與不同組織，再利用標準試片的實驗模型，求轉換關係方程式，並進行找出適合方程式，並求修正方程式，接著製程精密度與驗證，提昇生產製程穩定性和預測準確度，且有效改善品質與減少基重均勻性的不良率，針對織布檢測使用監督式學習演算法與分段式的方程式，並準確率誤差的比較，進而提出有效自動監督式學習演算法，找出準確量測值。
經由光學近紅外線檢測系統得到光訊號轉換電壓訊號，求修正的關係方程式，再進行基重檢測，並求出適合指數型、連續式最小平方法、分段式最小平方法、監督式學習法、修正方程式等，經求出適合方程式與驗證。其實驗結果監督式學習法，可達良好線上測試，接著定義製程品質能力分析與常態分佈，可降低不織布原料的成本，不織布生產製程速度在120 m/min以下，以1000組樣本，經實驗製程精密度Cp 是1.66，並滿足其條件。因此，應用監督學習法可有效的提升不織布製程之生產能力品質穩定性。

The purpose of this thesis study is to develop a method of optical transmission inspection of the basis weight on-line, by combining the modified least squares and optical processing technique. A near infrared light transmission inspection is applied production of equipment nonwoven fabrics to detect the basis weight and support the producing quality. Using least squares method, the parameter transfer equations of the piecewise polynomials functions between the measured voltage and the nonwoven basis weight are found. Supervised learning method is adopted to improve the producing capability. Obvious, the equations and supervised learning method is effective to improve measures the range, producing capability and support the producing quality. This process is developed to significantly target toward improving the mass quality analysis of the nonwoven material.
The real-time scanning width piecewise least squares method and area-based strategy for determining based on the process quality of nonwoven manufacturing. To avoid the influence of ambient factors, the compensation controls device are adopted and successfully showed. Subsequently, the modified least squares method is used to obtain the suitable parameter transformation between the measured voltage and the nonwoven fabrics basis weight. The piecewise least squares method was obtained as the parameter transfer equation. We consider estimating and testing Cp with the presence of on-line basis weight measurement errors. To obtain the true process precision Cp are presented to practitioners for their factory applications. In this study, a NIR transmission-based inspection for the basis weight of to improve quality production process, to avoid production flaws and to reduce the production costs are the major issues of the manufacturing industry. The apparatus basically consists of a light emitter mounted parallel to a light receiver. The light is emitted from the light emitter. Residual light is received by the receiver after being transmitted through the nonwoven fabric. An equation acquired by using the Beer–Lambert law, the parameter transfer equations of the equation functions between the measured voltage and the nonwoven basis weight are found. Optical inspection techniques can be also used in which the optical modulated to find a modified equation, then obtain the non-woven basis weight inspected on-line and verified by quality capability of process. A modified equation that can be used to reduce the uniformity and decrease the basis weight density. The potential of an optical sensor with increased sensitivity the range for finding the equations, near infrared light detecting the basis weight for a nonwoven material, to predict quality capability of nonwoven fabrics.
In the proposed algorithm the supervised learning for finding polynomials the equations between the measured voltage and the nonwoven basis weight are found, the error deviation inspection works online and accuracy prediction. The verification accuracy prediction has been conducted to illustrate the performance of the proposed inspection algorithm by a dynamic of experiments nonwoven fabrics.Parameter transfer equations, is adopted to improve the producing capability. It is shown that the capability index of process Cp is over 1.66 under 1000 testing samples when the supervised learning algorithm is used.

第一章 緒論 1
1-1 研究動機與目的 2
1-2 文獻回顧 3
1-2-1不織布製程均勻度檢測系統背景 3
1-2-2自動光學檢測基重系統研究 8
1-2-3最小平方法與多項式方法研究 9
1-2-4監督式學習法之研究 10
1-2-5基重檢測系統評估製程能力研究 11
1-3 不織布基重檢測流程架構 12
1-4 論文架構 17
第二章 光學穿透式檢測不織布基重系統模式 19
2-1 光學穿透式檢基重轉換基本原理 19
2-1-1 以同厚度不同基重 19
2-1-2 以不同厚度不同基重 22
2-1-3 不織布不同種類試片 23
2-1-4 求指數修正方程式 24
2-2 建立最小平方近似法與參數轉換模式 25
2-2-1 最小平方近似法 25
2-2-2 一元高次多項式 25
2-2-3 參數轉換方程式 26
2-3 監督式學習法與統計模式建立 27
2-3-1監督式學習法 27
2-3-2統計決策理論與統計法 27

2-4 製程能力分析模式建立 28
2-4-1製程能力精密度 29
2-4-2評估製程過程指數 30
第三章 30
3-1實驗方法 30
3-1-1設備與系統設定基重檢測系統架構 31
3-1-2標準試片實驗架構 32

3-2 近紅外線檢測裝置設計 32
3-2-1低功率補償電路設計 34
3-2-2高功率補償電路設計 36
3-2-3濕度對補償電路的影響 37
3-2-4溫度對補償電路的影響 38
3-2-5震動對檢測電路的影響 38
3-2-6低功率補償後量測訊號 39
3-2-7高功率補償後量測訊號 40
3-3實驗材料 42
3-4實驗參數轉換程序 44

第四章 參數轉換非線性關係式的建構 44
4-1 指數關係式 45
4-2 不同原料評估實測值的關係 45

第五章 結果與討論 47
5-1一般式在監督學習法的比較 47
5-1-1原料與結構相同連續的方程式 47
5-1-2原料與結構相同分段的方程式 48
5-1-3原料與結構不同分段的方程式 49

5-2一元三次多項式擬合 51
5-2-1連續模式 51
5-2-2分段模式 52
5-3多項式監督式學習法擬合 54
5-3-1連續模式 54
5-3-2分段模式 55
5-4 最佳化一般式與多項式準確性評估的比較 56
5-5一元三次多項式製程能力驗證的比較 58
5-5-1連續模式 58
5-5-2分段模式 59
5-6監督式學習法一元三次多項式製程能力驗證的比較 61
5-6-1連續模式 61
5-6-2分段模式 62
5-7一般式與多項式監督式學習法製程能力驗證的比較 64
5-7-1一種原料與結構 64
5-7-2三種原料與結構 67

第六章 結論 74

參考文獻 76

參考文獻
﹝1﹞R.Stojanovic, Real-Time Imaging, Vol 7, pp.507-518,2001.
﹝2﹞R.Veerabadran, Textile Res J., Vol 66, pp.257-264, 1996.
﹝3﹞ASTM D6242-98, Standard Test Method for Mass Unit Area of Nonwove -n Fabrics, 2004.
﹝4﹞T.S.Newman and A.K.Jain., Computer Vision and Image Understanding, Vol 61, pp.321-326, 1995.
﹝5﹞D.Brzakovic and N.Vujovic, Pattern Recognition, Vol 29, pp.1401-1406, 1996.
﹝6﹞J.Liu, B.Zuo, X.Zeng, P.Vroman, and B.Rabenasolo, Expert Systems with Applications, Vol 37, pp.2241-2248, 2010.
﹝7﹞K.T.Laua, Susan Baldwin and Martina, O’Toole, Analytica Chimica Acta, Vol 5, pp.111-116, 2006.
﹝8﹞Jurgen adamy, Journal of Approximate Resoning, Vol. 16, pp.25-42, 1997.
﹝9﹞H.Bai, H.Wang, M.T Soylemz and N.Munro, Control Engineering Practie, Vol 9, pp.621-630, 2001.
﹝10﹞M.C. Liang, H.C. Yi, and Qian Lin, Applied Radiation and Isotopes, Vol 67, pp.1974-1979, 2009.
﹝11﹞W.H.Liu, Kong Li, Qu Tan, and Jing Jing Cheng, Applied Radiation and Isotopes, Vol 57, pp.353-357, 2002.
﹝12﹞H.C. Lien, and C.H. Liu, Text. Res. J., Vol 76, pp.547-556, 2006.
﹝13﹞M.Whitaker, Measurement of Basis Weight for Nonwovens a Review of Transducers & Methods of Data Presentation, NDC System,1th ed. pp.193-196, 1992.
﹝14﹞J. Laitinen, Optics and lasers in Engineering, Vol 29, pp.385-392, 1998.
﹝15﹞R. K. Aggarwal, W. R.Kennon, and I.Porat, J.Textile Inst, Vol 83, pp. 386-398, 1992.
﹝16﹞P.A.Boecherman, Tappi Journal, Vol 13, pp.166-172, 1992.
﹝17﹞F.Thorr, J.Y.Drean, and D.Adolphe, Textile Res. J., Vol 69, pp.162-168, 1999.
﹝18﹞Z.Yan, and R. R.Bresee, J. Textile Inst., Vol 89, pp.320-336,1998.
﹝19﹞P. E. Ciddor, Appl. Opt., Vol 35, pp.1566-1572, 1996.
﹝20﹞B. C. Wilson, and S. L. Jacques, IEEE J. Quan. Electro, Vol 26, pp.2186 -2192, 1990.
﹝21﹞H. Golnabi, Optics and Lasers in Engineering, Vol 38, pp.537-545, 2002.
﹝22﹞H.Phan, Six Sigma Process Control, Guide to Standardized Process Control Practices, Motorola Inc, 1th ed., 1998.
﹝23﹞A. M. Alghanim and N.R. Aukland, Computers & Industrial Engineer -ing, Vol 31, pp.389-395,1996.
﹝24﹞W.L. Pearn, and P.C. Lin, Computers & Industrial Engineering, Vol 15, pp.351- 358, 2004.
﹝25﹞W. J. Smith, Modern Optical Engineering, Vol 4, pp.26-42, 2007.
﹝26﹞C.S Lin, Optics and Laser Technology, Vol 43, pp.218, 2011.
﹝27﹞J.Meng, A.M.Seyam, and S.Batra, Textile Res.J., Vol 69, pp.155-161, 1999.
﹝28﹞W. Xu, M.H. Jericho, H.J. Kreuzer, and I.A. Meinertzhagen, Opt. Letter, Vol 28, pp.164-170, 2003.
﹝29﹞G.Rosati, G.Boschetti, A.Biondi, and A.Rossi, Optics and Lasers in Engi neering, Vol 47, pp.379-386, 2009.
﹝30﹞E.Allaria, S. Brugioni, S. De Nicola, P.Ferraro, S.Grilli and M.Meucci, Optics Communications, Vol 215, pp.257-263, 2003.
﹝31﹞J. Laitinen, Optics and lasers in Engineering, Vol 29, pp.385-392 , 1998.
﹝32﹞J. Liu, B. Zuo, X.Zeng, P.Vroman, and B. Rabenasolo, Expert Systems
with Applications, Vol 37, pp.2241-2248, 2010.
﹝33﹞O.Krasnykov, A.Karabchevsky, A.Shalabney, M. Auslender, and I.A. Halim, Optics Communications, Vol 284, pp.1435-1438, 2011.
﹝34﹞M.A. Khashan, and A.M. El.Naggar, Optics Communications, Vol 174, pp.445-453, 2000.
﹝35﹞P.F.Luo, Optics and Lasers in Engineering, Vol 42, pp.563-571, 2004.
﹝36﹞L. Armando R. Rivera, Comput. Ind. Engineering, Vol 29, pp.55-61,
1995.
﹝37﹞V.N.Vapnik, Statistical Learning Theory, New York, John Wiley, 1th ed., 1998.
﹝38﹞P.F.Mc Coy, Quality Progess, 2th ed., pp.49-55, 1991.
﹝39﹞N.F.Hubele, and Frederick P.Lawrence, Computers ind. Engineering, Vol 29, pp. 55-58, 1995.
﹝40﹞S.Kotz, and CR.Lovelace, Process Capability Indices in Theory and Practice, London Arnold, 2th ed. 1998.
﹝41﹞B.T.Ramakrishnan, P.Sandborn and M.Pecht, Microelectronics reliabil- ity, Vol 14, pp.2067-2070, 2001.
﹝42﹞H.Phan, Six sigma process control, Motorola Inc, 1th ed., 1998.
﹝43﹞L.A.Rosas Rivera, Computerind. Engng, Vol 29, pp.55-58, 1995.
﹝44﹞R.A.Boyles, Journal of Quality Technology, Vol 23, pp.17-26, 1991.
﹝45﹞C.W.Wu, Economics, Vol 117, pp.338-359, 2009.
﹝46﹞D.B.M, Journal of Materials Processing Technology, Vol 162, pp.736- 743, 2005.
﹝47﹞V.N.Vapnik, IEEE Transactions on Neural Networks, Vol 10, pp.988- 999, 1999.
﹝48﹞J. W. S Hearle and W. E Morton, Physical Properties of Textile Fibres, 2th ed. pp.15-42, 2008.
﹝49﹞S. Zeroian and M. K. Inglesby, Journal of Applied Polymer Science, Vol
71, pp.1163, 1999.
﹝50﹞V.N.Vapnik, The Nature of Statistical Learning Theory Springer, New York, 1st ed., 1995.
﹝51﹞V. Cherkassky and F. Mulier, Learning from Data: Concepts, Theory, and Methods, New York, John Wiley, 1th ed., 1998.
﹝52﹞E.Hecht, Optics, Addison Wosley, 2th ed., 2002.
﹝53﹞ASTM D5729-95, Standard Test Method for Thickness of Nonwoven Fabrics, 1995.
﹝54﹞ASTM D5199-01, Standard Test Method for Measuring the Nominal Thickness of Geosynthetics, 2001.