本論文的研究目的為利用增加軟鏈段長度的苯乙烯三嵌段共聚物(Enhanced rubber segment，ERS)提升聚丙烯(Polypropylene，PP)之物理性質並保有原光學性質，藉此提升市面嬰兒餐具之物理性質或光學性質的不足，並達到降低汰換率與節能環保的概念。經由參考不同的苯乙烯三嵌段共聚物文獻，瞭解材料物理性質與光學性質的變化，並找出適合本研究分析產品品質的混煉比例區間，再配合多項加工參數詳細分析品質間的變化，最後找出所希望的產品品質加工參數組。研究方法首先以田口法結合層級法去分析品質之影響並且獲得區域性最佳化參數，再透過田口實驗數據與倒傳遞類神經網路預測與模擬田口實驗設計法所得到的加工參數與產品品質之間的交互影響關係，之後以產品品質為粒子群優法的適應性函數，並將加工參數範圍作為粒子群優法的邊界條件，透過不斷地更新與迭代找出全域性最佳之加工參數組合。研究結果顯示，田口法結合層級分析法與倒傳遞類神經結合粒子群優法，能有效率地決策最佳加工參數，而倒傳遞類神經結合粒子群優法求得之最佳品質優於田口法與層級分析法所得之品質，且相較於市面產品各品質表現均有效的提升。

The aim of this study is to upgrade mechanical properties and maintain optical properties of Polypropylene (PP) by Enhanced rubber segment (ERS) to enhance baby tableware qualities also achieve the concept of energy saving and low replacement rate. By reading different literatures will help us to understand the physical and optical properties of material and locate suitable mixing ratios for this study, then we can use some parameters for further analysis to find the optimal qualities of product. In the beginning, we will discuss the influence of the composite’s qualities in different ratios and find local optimal parameters by using Taguchi method with Analytic Hierarchy Process (AHP). After that, we will create a math model on Back-Propagation Neural Network (BPNN) by stimulating the interaction of parameters and qualities from Taguchi experimental design. Once BPNN makes a successful prediction, we will be able to use particle swarm optimization method to analyze the math model and set the parameter’s range as boundary conditions. Particle swarm optimization will constantly update and iterate until locating the global optimal parameters. As a conclusion, using Taguchi method along AHP and BPNN with particle swarm optimization will efficiently pin down the optimal parameters, but the final performance reviews that BPNN with particle swarm optimization is slightly more precise, offering a better outcome than Taguchi method along AHP. The final performance also has much better qualities than the products on the market.

參考文獻
[1] http://www.kraton.com/products/Kraton_G_SEBS_SEPS.php#
[2]曹育智，“應用類神經網路與基因遺傳以算法於聚丙烯/苯乙烯三嵌段共聚物複合材料之多品質加工參數最佳化”國立台灣科技大學，材料科學與工程學系研究所碩士論文，2013。
[3] S. N. Purwar and A. K. Gupta, “Tensile Yield Behavior of PP/SEBS blends,” Journal of Applied Polymer Science, Vol. 29, No. 11, pp. 3513-3531, 1984.
[4] A. K. Gupta, “Mechanical Properties and Morphology of PP/SEBS
　 /PC Blends,” Journal of Applied Polymer Science, Vol. 53, No. 1, pp. 1-17, 1994.
[5] T. 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.
[6] H. Nagashima and K. Kikuchi, “Weight Reduction and Paint-Less of Parts of Automobile by Polypropylene/Elastomer Blends,” Proceedings of The FISITA 2012 World Automotive Congress, Vol. 199, pp. 145-158, 2012
[7] S. H. Qin, H. Liu, M. M. Zhang, M. He and J. Yu, “Effect of Elastomer on Crystallization, Transparence, Morphology and Mechanical Properties of Transparent PP Containing Nucleating Agent,” Polymer-Plastics Technology and Engineering, Vol. 51, pp. 867-872, 2012
[8] C. Grein, M. Gahleitner and K. Bernreiner, “Mechanical and Optical Effect of Elastomer Interaction in Polyprepylene Modification: Ethylene-Propylene Rubber, Poly-(Ethylene-Co-Octene) and Styrene-Butadiene Elastomers,” Express Polymer Letters, Vol. 6, No. 9, pp. 688-696, 2012
[9] F. Clemens, B. Koll, T. Graule, T. Watras, M. Binkowski, C. Mattmann and I. Silveira, “Development of Piezoresistive Fiber Sensors, Based on Carbon Black Filled Thermoplastic Elastomer Compounds, for Textile Application,” Advances in Science and Technology, ISSN: 1622-0356, Vol. 80, pp. 7-13, 2012.
[10]C. Zhao, X. Xu, J. Chen and F. Yang, “Optimization of Preparation Conditions of Poly (Vinylidene-Fluorude)/Graphene Oxide Microfiltration by The Taguchi Experimental Design,” Desalination, Vol. 334, pp. 17-22, 2014.
[11]G. Nandi, S. Datta, A. Bandyopabhyay and P. Pal, “Application of PCA-Based Hybrid Taguchi Method for Correlated Multi Criteria Optimization of Submerged Are Weld,” International Journal Advanced Manufacture Technology, Vol. 45, pp. 276-286, 2009.
[12]C. K. Venil, “Taguchi Experimental Design for Medium Optimization for Enhanced Protease Production by Bacillus Subtilis HB04,” E-Journal of Science and Technology, Vol. 4, NO. 4, 2015.
[13]S. Askari, R. Halladj, M. Nazari, “Statistical Analysis of Sonochemical of SAPO-34 Nanocrystals Using Taguchi Experimental Design,” Materials Research Bulletin, Vol. 48, pp. 1851-1856, 2013.
[14]K. Chockalingam, N. Jawahar, K. N. Ramanathan and P.S. Banerjee, “Optimization of Stereo Lithography Process Parameters for Part Strength Using Design of Experiments,” International Journal of Advanced Manufacturing Technology, Vol. 29, pp. 79-88, 2006.
[15]S. Akincoglu, H. Gokkaya and L. Uygur, “The Effect of Cryogenic-Treated Crabide Tools on Tool Wear and Surface Roughness of Turning of Haetelloy C22 Based on Taguchi Method,” International Journal of Advance Manufacturing Technology, Vol. 82, Issue 1, pp. 303-314, 2016.
[16]H. M. Hasanien, “Design Optimization of PID Controller in Automatic Voltage Regulator System Using Taguchi Combined Genetic Algorithm Method,” IEEE Systems Journal, Vol. 7, No. 4, pp. 852-831, 2013.
[17]Z. H. Xu, S. C. Wang, Z. W. Zhang, T. S. Chin, and C. K. Sung, “Optimization of Magnetizing Parameters for Multiple Magnetic Scales Using the Taguchi Method,” IEEE Transactions on Magnetics, Vol. 51, No. 1, 2015.
[18]K. Zhü, O. Cooper, S. Yang and Q. Dong, “An Extension of The AHP Dummy Pivot Modeling Applied to The Restructuring of The Iron and Steel Industry in China,” Vol. 61, No. 2, pp. 370-380, 2014.
[19]M. L. Tseng, Y. H. Lin, and A. S. F. Chiu, “Fuzzy AHP Based Study of Cleaning Production Implementation in Taiwan PWB Manufacturer,” Journal of Cleaner Production, Vol. 17, pp. 1249-1256, 2009.
[20]K. Govindan, M. Kaliyan, D. Kannan and A. N. Haq, “Barriers Analysis for Green Supply Chain Management Implementation in Indian Industries Using Analytic Hierarchy Process,” International Journal of Production Economics, Vol. 147, pp. 555-568, 2014.
[21]M. K. Tiwari, N. Raghavendra, S. Agrawal, and S. K. Goya, “A Hybrid Taguchi-Immune Approach to Optimize an Integrated Supply Chain Design with Multiple Shipping,” European Journal of Operational Research, Vol. 1, No. 9, pp. 201-223, 2009.
[22]W. N. Pi and C. LOW, “Supplier Evaluation and Selection Via Taguchi Loss Functions and An AHP,” International Journal of Advanced Manufacturing Technology, Vol. 27, pp. 625-630, 2006.
[23]K. Reza, M. Senior and D. Reza, “The Application of Analytic Hierarchy Process to Determine Proportionality Constant of The Taguchi Quality Loss Function,” IEEE Transactions on Engineering Management, Vol. 55, No. 2, pp. 340-348, 2008.
[24]林信安，2014，聚乳酸/奈米雲母複合材料之多品質加工參數最佳化，國立台灣科技大學，材料科學與工程學系研究所碩士論文。
[25]F. A. Alkaabneh, M. Barghash, I. Mishael, “A Combined Analytical Hierarchical Process (AHP) and Taguchi Experimental Design (TED) for Plastic Injection Molding Process Setting,” The International Journal of Advanced Manufacturing Technology, Vol. 56, pp. 679-694, 2013.
[26]R. Sivakumar, D. Kannan and P. Murugesan, “Green Vendor Evaluation and Selection Using AHP and Taguchi Loss Function in Production Outsourcing in Mining Industry,” ScienceDirect, Vol. 46, Part 1, pp. 64-75, 2015.
[27]D. C. Chen and C. K. Huang, “Study of Injection Molding Warpage Using Analytic Hierarchy Process and Taguchi Method,” Advances in Technology Innovation, Vol. 1, No. 2, 2016.
[28]Y. H. Tsai, J. C. Chen and S. J. Lou, “An In-Process Surface Recognition System Based on Neural Networks in End Milling Cutting Operations,” International Journal of Machine Tools and Manufacture, Vol. 39, pp. 583-605, 1999.
[29]C. F. Yao and W.T. Chien, “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.
[30]M. Suman, M. V. G. Rao, A. Hanumaiah and K. Rajesh, “Solution of Economic Load Dispatch Problem in Power System Using Lambda Iteration and Back Propagation Neural Network Methods,” International Journal on Electrical Engineering and Informatics, Vol. 8, No. 2, 2016.
[31]A. Tortum, N. Yayla, C. Celik and M. Gokdag, “The Investigations of Model Selection Criteria in Artificial Neural Networks by The Taguchi method,” Statistical Mechanics and its Applications, Vol. 386, No. 1, pp. 446-468, 2007.
[32]W. Baoguo, G. Furong and Y. Polock, “Neural Network Approach to Predict Melt Temperature in Injection Processes,” Chinese Journal of Chemical Engineering, Vol. 8, pp. 326-331, 2000.
[33]V. Sigh, I. Gupta and H. Guapt, “ANN-Based Estimator for Distillation Using Landenberg-Marquardt Approach,” Engineering Applications of Artificial Intelligence, Vol. 20, No. 2, pp. 249-259, 2007.
[34]M. A. Moghaddam and F. Kolahan, “An Optimised Back Propagation Neural Network Approach and Simulated Annealing Algorithm Towards Optimisation of EDM Process Parameters,” International Journal of Manufacturing Research, Vol. 10, Issue3, 2015.
[35]F. Jafarian, M. Taghipour and H. Amirabadi, “Application of Artificial Neural Network and Optimization Algorithms for Optimizing Surface Roughness, Tool Life and Cutting Forces in Turning Operation,” Journal of Mechanical Science and Technology, Vol. 27, pp. 1469-1477, 2013.
[36]C. Ren, N. An, J. Wang, L. Li, B. Hu and D. Shang, “Optimal Parameters Selection for BPNN Based on Particle Swarm Optimization: A Case Study of Wind Speed Forecasting,” Knowledge-Based Systems, Vol. 56, pp. 226-239, 2014.
[37]Y. Xu, Q. Zhang, W. Zhang and P. Zhang, “Optimization of Injection Molding Process Parameters to Improve The Mechanical Performance of Polymer Product Against Impact,” The International Journal of Advanced Manufacturing Technology, Vol. 76, pp. 2199-2208, 2015.
[38]R. C. Eberhart and J. Kennedy, “Particle swarm optimization,” Procee-dings of the IEEE International Conference on Neural Networks, Piscataway, pp. 1942-1948, 1995.
[39]Z. Zexuan, Z. Jiarui and J. Zhen, “DNA Sequence Compression Using Adaptive Particle Swarm Optimization-Based Mathematic Algorithm,” IEEE Transaction Journal on Evolutionary Computation, Vol. 15, No. 5, pp. 643-658, 2011.
[40]R. Taormina and K. W. Chau, “Neural Network River Forecasting with Multi-Objective Fully Informed Particle Swarm Optimization,” Journal of Hydroinformatics, Vol. 17, Issue 1, 2015.
[41]K. Lee and J. Kim, “Multi Objective Particle Swarm Optimization with Preference-Based Sort and Its Application to Path Following Footstep Optimization for Humanoid Robots,” IEEE Transactions Journal on Evolutionary Computation, Vol. 17, No. 6, pp. 755-766, 2013.
[42]Y. Fu, “Phase Angle-Encoded and Quantum-Based Particle Swarm Optimization Applied to Three-Dimensional Route Planning for UAV,” IEEE Transactions on Systems and Cybernetics-Part A: Systems and Humans, Vol. 42, No. 2, pp. 511-526, 2012.
[43]李輝煌，2008，“田口方法-品質設計的原理與實務”，高立圖書有限公司，行政院新聞局局版臺業字第1423號。
[44]榮泰生，2011，“Expert Choice在分析層級程序法(AHP)之應用”，五南圖書有限公司，ISBN: 9789571163024。
[45]黃國源，2015，“類神經網路”，全華圖書，ISBN: 9789864630400。
[46]Z. Vuluga, D. M. Panaitescu, C. Radocivi, C. Nicolae and M. D. Lorga, “Effect of SEBS on Morphology, Thermal and Mechanical Properties of PP/Organoclay Nano-composites,” Polymer Bulletin, Vol. 69, Issue 9, pp. 1073-1091, 2012.
[47]M. Malha, S. Nekhlaoui, H. Essabir, K. Benmoussa, M. O. Bensalah, F. E. Arrakhiz, R. Bouhfid and A. Qaiss, “Mechanical and Thermal Properties of Compatobilized Polypropylene Reinforced by Wovendoum,” Journal of Applied Polymer Science, Vol. 130, Issue 6, pp. 4347-4356, 2013.
[48]C. W. Lou, C. L. Huang, Y. J. Pan, Z. I. Lin, X. M. Song and J. H. Lin, “Crystallization, Mechanical and Electromagnetic Properties of Conductive Polypropylene/SEBS Composite,” Journal of Polymer Research, 23:84, 2016.