臺灣博碩士論文加值系統

摘 要
製造人造纖維最常使用熔融紡絲法，而初生纖維最重要的物理性質以細度及斷裂強度為主，因加工參數是以螺桿轉速、螺桿五段加熱溫度、齒輪幫浦轉速、紡嘴溫度、冷卻溫度、冷卻風速及捲取轉速等會影響其物性。首先，選擇適合的直交表應用於實驗計劃以進行實驗，配合SN比及變異數分析，了解加工參數對品質之影響程度，並確認實驗之再現性；應用倒傳遞類神經網路結合田口法，藉由之前的實驗數據加以學習訓練調整網路權重值，可改善在建立動態系統模式設計上之問題，以減少誤差進而達到收斂，最後採用基因演算法尋找品質特性之最佳化，進而獲得最佳化的加工參數組合。

The most popular and economic way to manufacture man-made fibers is melt spinning. In general, rotation speeds of an extruder and a gear pump, extruder temperature, spinning temperature, linear speed of a take-up equipment, and air cooled temperature and speed are a typical set of operating parameters to most affect the important properties of denier and tenacity of as-spun yarn. First, the suitable orthogonal array is used to plan experiments. An orthogonal array, the signal-to-noise ratio, and ANOVA (Analysis of Variance) are employed to investigate performance characteristics and to determine reproducibility of confirmation experiment in the melt spinning. A new method of dynamic model design that combines the BPNN (Back-propagation Neural Network) and Taguchi techniques to improve engineering design is proposed. The BPNN focuses on choosing parameters to study its the convergence. With the information and data collected from the experiments, we established a BPNN to provide accurate estimations. Finally, by utilizing the genetic algorithm, the optimal combination of the machining parameters can be found.

目 錄
摘 要I
AbstractII
誌謝III
目 錄IV
圖索引VI
表索引VII
第一章 緒論1
1.1 文獻回顧1
1.2 研究目的6
1.3 研究步驟6
第二章 熔融紡絲8
2.1 壓出機9
2.2 齒輪幫浦10
2.3 紡絲延伸過程11
第三章 分析理論探討12
3.1 田口實驗規劃法13
3.1.1 品質控制技術13
3.1.2 工業實驗設計14
3.1.3參數設計15
3.1.4 變異數分析16
3.2 倒傳遞類神經網路17
3.2.1 集成函數19
3.2.2 轉換函數20
3.2.3 尺度化20
3.2.4 加權值與偏權值之調整21
3.2.5 網路之演算法22
3.3 基因演算法23
3.3.1 基因演算法之特性23
3.3.2 演算法步驟24
3.4 TOPSIS法評估多目標之性能指標28
3.4.1 品質特性權重值之選擇29
3.4.2 TOPSIS之分析步驟31
第四章 實驗規劃及結果討論34
4.1 實驗規劃設計34
4.2 實驗步驟36
4.3 實驗結果分析36
4.4 最適條件之預估與驗證實驗40
4.5 倒傳遞類神經網路之應用44
4.6 基因演算法結合TOPSIS法之應用49
第五章 結論52
參考文獻54
附錄A58

參考文獻
[1] 吳偉欽，”聚丙烯纖維染色性之探討”，絲織園地，第26期。
[2] S. Kase and T. Matsuo, “Studies on Melt Spinning. I. Fundamental Equation on the Dynamics of Melt Spinning”, Journal of Applied Polymer Science, Vol. 3, pp. 2541-2554 (1965).
[3] S. Kase and T. Matsuo, “Studies on Melt Spinning. II. Steady-State and Transient Solutions of Fundamental Equations Compared with Experimental Results”, Journal of Applied Polymer Science, Vol. 11, pp. 251-287 (1967).
[4] A. Ziabicki, Fundamentals of Fiber Formation, John Wiley, London (1976).
[5] Z. Tadmor and C. G. Gogos, Principle of Polymer Processing, John Wiley, New York (1979).
[6] A. Dutta and V. M. Nadkarni, ”Identifying Critical Process Variable in Poly(ethylene Terephthalate) Melt Spinning”, Textile Research Journal, Vol. 54, No. 1, pp. 35-42 (1983).
[7] K. W. Hutchenson, D. D Edie and D. M. Riggs, ”Radial Temperature Differences During the Melt Spinning of Fibers”, Journal of Applied Polymer Science, Vol. 29, pp. 3621-3640 (1984).
[8] D. G. Young and M. M. Denn, ”Disturbance Propagation in Melt Spinning”, Chemical Engineering Science, Vol. 44, No. 9, pp. 1807-1818 (1989).
[9] C. Jinan, T. Kikutani, A. Takaku and J. Shimizu, ”Nonisothermal Orientation-Induced Crystallization in Melt Spinning of Polypropylene”, Journal of Applied Polymer Science, Vol. 37, pp. 2683-2697 (1989).
[10] R. H. Frith and W. Scott, ”Wear in External Gear Pumps: a Simplified Model”, Wear, Vol. 172, No. 2, pp. 121-126 (1994).
[11] P. L. Shah, E. Steward and G. Yazbak, ”A Study of the Effect of the Extrusion Variables and Screw Design on the Thermal and Rheological Characteristics of Acetal”, Polymer Engineering and Science, Vol. 34, No. 15, pp. 1196-1201 (1994).
[12] E. Andreassen, O. J. Myhre, F. Oldervoll, E. L. Hinrichsen, K. Grostad and M. D. Braathen, ”Nonuniform Cooling in Multifilament Melt spinning of Polypropylene Fibers：Cooling Air Speed Limits and Fiber-to-Fiber Variations”, Journal of Applied Polymer Science, Vol. 58, pp. 1619-1632 (1995).
[13] K. Wilczynski, ”Computer Model for Single-Screw Plasticating Extrusion”, Polymer-Plastics Technology and Engineering, Vol. 35, No. 3, pp. 449-477 (1996).
[14] V. B. Gupta, S. A. Mondal and Y. C. Bhuvanesh, ”Spinning Speed-Throughput Rate Relationships for Polyester, Nylon, and Polypropylene Fibers”, Journal of Applied Polymer Science, Vol. 65, pp. 1773-1788 (1997).
[15] 田口玄一，田口實驗計劃法，滄海出版社(1997)。
[16] D. M. Byrne and S. Taguchi, The Taguchi Approach to Parameter Design, Quality Progress, pp.19-26 (1987).
[17] R. S. Chen , H. H. Lee and C. Y. Yu, ”Application of Taguchi Method on the Optimal Process Design of an Injection Model PC/PBT Automobile Bumper”, Composite Structures, Vol. 39, No. 3-4, pp. 209-214 (1997).
[18] 白賜清，工業實驗計劃法，中華民國品質管制學會(1991)。
[19] 林秀雄，田口方法與品質工程，新知企管(1991)。
[20] 鍾清章 校訂，田口式品質工程導論，中華民國品質管制學會發行(1989)。
[21] C. L. Hwang and K. Yoon, Multiple Attribute Decision Making-Method and Applications, A State-of-the-Art Survey, Springer-Verlag, New York (1981).
[22] 陳志堅，應用模糊理論於田口線外品管多重品質特性最佳化之問題研究，國立交通大學工業工程研究所碩士論文(1994)。
[23] C. L. Hwang and S. J. Chen, Fuzzy Multiple Attribute Decision Making-Method and Applications, A State-of-the-Art Survey, Springer-Verlag, New York (1992).
[24] L. I. Tong and C. T. Su, ”Optimizing Multi-Response Problems in the Taguchi Method by Fuzzy Multiple Attribute Decision Making”, Quality and Reliability Engineering International, Vol. 13, No. 1, pp. 25-34 (1997).
[25] 陳宏明，多種品質特性在動態系統中之研究，私立中原大學工業工程研究所碩士論文(1994)。
[26] 葉韾雅，動態系統多重品質特性最佳化之研究，國立交通大學工業工程研究所碩士論文(1997)。
[27] 陳姣燕，應用雙反應曲面分析法於動態系統多重品質特性最佳化之研究，國立交通大學工業工程研究所碩士論文(1998)。
[28] 葉怡成，類神經網路模式應用與實作，儒林圖書有限公司(1993)。
[29] 吳嘉哲，類神經網路式最佳參數設計法則，國立中興大學機械工程研究所碩士論文(1999)。
[30] G. J. Wang, Y. Z. Yang and K. Chang, ”A MDRS Network Based Intelligent Vision System”, the International Journal of Knowledge-Based Intelligent Engineering Systems, Vol.2, No. 1, pp. 17-31 (1998).
[31] G. J. Wang, J. C. Tsai, P. C. Tzeng and T. C. Cheng, ”Neural-Taguchi Method for Robust Design Analysis”, Journal of the Chinese Society of Mechanical Engineers, Vol. 19, No. 2, pp. 223-230 (1998).
[32] 張賢燦，分群方法及灰關聯理論應用於類神經網路學習參數之調整研究，國立台灣科技大學機械工程系碩士論文(2000)。
[33] M. Gen and R. Cheng, Genetic Algorithms and Engineering Design, John Wiley, New York (1997).
[34] S. Sette, L. Boullart, L. V. Langenhove and P. Kiekens, ”Optimizing the Fiber-to-Yarn Production Process with a Combined Neural Network / Genetic Algorithm Approach”, Textile Research Journal, Vol. 67, No. 2, pp. 84-92 (1997).
[35] 蔡子琦，類神經網路與基因遺演算法於WEDM加工參數最佳化應用，國立台灣大學機械工程學研究所碩士論文(1999)。
[36] J. A. Covas, A. G. Cunha and P. Oliveira, ”An Optimization Approach to Practical Problems in Plasticating Single Screw Extrusion”, Polymer Engineering and Science, Vol. 39, No. 3, pp. 443-456 (1999).