臺灣博碩士論文加值系統

射出成型是高分子材料最常使用的製造方法，而射出成型製程的參數設定，因太依賴設計者的經驗或試誤法，所以會引起時間上的浪費。因此有必要在加工前有設定加工參數的正確數據資訊。本論文採用苯乙烯三嵌段聚合物與聚丙烯之複合材料，探討射出成型最佳拉應力與硬度之加工參數，其中加工參數包含射出溫度、混煉比例、螺桿轉速以及射出速度；並應用類神經網路來預測加工參數與產品品質之間的交互影響。最後，以生產品質作為遺傳算法的目標函數，並以預測的產品品質作為遺傳算法的拘束條件，之後我們透過複製、交配以及突變的計算找出最大適應度值的加工參數。由研究結果顯示，結合類神經網路與基因遺傳演算法具有找出射出成型最佳加工參數的效果。

Abstract
The injection molding is the mostly used manufacturing method for Polymers. The processing parameters setting of injection molding heavily depends on designers' experience or trial-and-error procedures, so it consumes much time. Thus, it is prerequisite to set up the correct processing parameters before processing. This paper uses a compound material of SEBS and polypropylene to investigate the optimal processing parameters of injection molding for optimizing tensile stress and hardness. The parameters include injection temperature, mixing ratio, screw speed and injection speed. The neural network model is applied to predict the reciprocal effects between processing parameters and product quality. For the genetic algorithm, it takes the product quality as the basis of the objective function and the quality predictions as the basis of constraint conditions. We calculate the maximum fitness value of the processing parameters with reproduction, crossover and mutation. The results show that the proposed method can find the optimum processing parameters of injection molding for multiple qualities.

目錄

摘要 I
ABSTRACT II
致謝 III
目錄 IV
圖索引 VI
表索引 VIII
第一章　緒論 1
1.1 前言 1
1.2 研究動機與目的 2
1.3 文獻回顧 3
1.3.1 苯乙烯三嵌段聚合物、聚丙烯與混煉製備3
1.3.2 預測模型建構 4
1.3.3 加工參數最佳化 5
1.4 論文架構 7
第二章　實驗材料與設備 8
2.1 材料介紹 8
2.1.1 苯乙烯三嵌段聚合物 8
2.1.2 聚丙烯 9
2.2 加工設備 11
2.2.1 射出成型機 11
2.2.2 單螺桿混煉機 13
2.3 材料分析儀器 14
2.3.1 熱重損失分析儀 14
2.3.2 熱示差分析儀 15
2.3.3 萬能拉力試驗機 16
2.3.4 蕭氏硬度計 18
第三章 類神經網路與基因遺傳演算 21
3.1 類神經網路 21
3.2 基因演算法 28
3.2.1 編碼 30
3.2.2 適應函數設計 31
3.2.3 複製 31
3.2.4 交配 33
3.2.5 突變 35
第四章　實驗規劃及結果討論 36
4.1 實驗材料 36
4.2 材料分析 37
4.3 實驗規劃 39
4.3.1 田口實驗規劃及實驗結果 39
4.3.2 倒傳遞類神經規劃及實驗結果 51
4.3.3 遺傳演算規劃及實驗結果 56
第五章　結論與未來展望 61
5.1 結論 61
5.2 未來展望 61
參考文獻 63

參考文獻
[1] A. K. Gupta, “ Mechanical properties and morphology of PP/SEBS
/PC blends, ” Journa of Applied Polymer Science, Vol.53, no.1, pp.1-17, 1994.
[2] A. K. Gupta, S.N. Purwar, “ Tensile yield behavior of PP/SEBS blends, ” Journal of Applied Polymer Science, Vol.29, no.11,
pp. 3513-3531, 1984.
[3] Tanrattanakul, Varaporn, “ Polypropylene/natural rubber thermoplastic elastomer: effect of phenolic resin as a vulcanizing agent on mechanical properties and morphology, ” Journal of Applied Polymer Science, Vol.112, pp.3267-3275, 2009.
[4] Y. C. Chen, “ Preparation and characterization of nano-silver doped sericite, ” Master Thesis, Department of Chemistry and Engineering, Chung Yuan Christian University, 2007.
[5] M. H. Chung, “ Study on weld-line of ABS thin-wall injection molding parts, “ Master Thesis, Department of Mechanical Engineering, Chung Yuan Christian University, 2001.
[6] Y. H. Tsai, J. C. Chen, S. J. Lou, “ An in-process
surface recognition system based on neural networks in End Milling Cutting Operations, ” International Journal of Machine Tools & Manufacture, Vol.39, pp.583-605, 1999.
[7] N. Costa, “ Artificial neural networks for data modelling of a plastic injection moulding process, ” Neural Information Processing, Vol.3, pp.1081-1087, 1999.
[8] C. Wang, “ Prediction for the Warpage of the plastic sheet based on artificial neural network, ” Electrical and Control Engineering, Vol.4, pp.1496-1498, 2010.
[9] W. Baoguo, G. Furong , Y. Polock, “ Neural network approach to predict melt temperature in injection processes, ” Chinese J. of Chem. Eng, Vol.8, pp.326-331, 2000.
[10] 劉惟信，1996，機械最佳化設計，金屬科技圖書股份有限公司，台北。
[11] 郭信川，王鴻鈞，1998，“遺傳演算法在最佳化設計問題之應用，”中國造船暨輪機工程學刊，第17 卷，第1 期，第39-48 頁。
[12] J. H. Holland, “ Adaptation in Natural and Artificial System, ” MIT Press, Cambridge, MA, USA, 1992.
[13] C. Kane, M. Schoenauer, “Topological optimum design using genetic algorithms, ” Controland Cybernetics, Vol.25, no.5, pp.1059-1087, 1996.
[14] S. Y. Woon, O. M. Querin, G. P. Steven, “ Structural application of a shape optimization method based on a genetic algorithm, ” Structural and Multidisciplinary Optimization, Vol.22, pp.57-64, 2001.
[15] F. Hereera, M. Lozano, “ Gradual distributed real-coded genetic algorithms, ” IEEE Transactions on Evolutionary Computation,, Vol.4, no.1, pp.43-63, 2000.
[16] 陳永昌，1998，“應用類神經網路與遺傳演算法對端銑削加工參數之最佳化”，國立高雄第一科技大學，機械工程研究所碩士論文。
[17] W.T. Chien, C.F. Yao, “ The development of the predictive model for metal machining parameters based on artificial neural network and genetic algorithm, ” Proceedings of The 14th National Conference on Mechanical, Engineering the Chinese Society of Mechanical Engineers, pp.468-475, 1997.
[18] 溫程雄，1998，“工具機最佳加工參數的設定，”國立中興大學，機械工程研究所碩士論文，台中。
[19] M. Dubey, “ Design of genetic algorithm based fuzzy logic power system stabilizers in multimachine power system, ” IEEE Power India Conference on Power System Technology , pp.1-6, 2008.
[20] Y. Cao, Y. Liu, “ Nozzle optimization of SF6 circuit breaker based on artificial neural network and genetic algorithm, ” International Conference on Electrical Machines and Systems, pp.222-225, 2008.
[21] J. J. Grefenstette, “Optimization of control parameters for genetic algorithms, ” IEEE Trans System, Vol.6, no.1, pp.122-128, 1986.