研究生: |
王致凱 Chih-Kai Wang |
---|---|
論文名稱: |
最低碳排放塑膠射出參數及產品重量預測分析研究 Analysis on Injection Molding Parameter for the Lowest Carbon Emission with Product Weight Prediction |
指導教授: |
陳炤彰
Chao-Chang Chen |
口試委員: |
黃明賢
Ming-Shyan Huang 劉士榮 Shih-Jung Liu 曾世昌 Shi-Chang Tseng 莊程媐 Cheng-Hsi Chuang |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 機械工程系 Department of Mechanical Engineering |
論文出版年: | 2021 |
畢業學年度: | 109 |
語文別: | 中文 |
論文頁數: | 190 |
中文關鍵詞: | 碳足跡 、低碳法 、機器學習 、品質預測 、田口方法 |
外文關鍵詞: | Carbon Footprint, Low Carbon Method, Machine Learning, Quality Prediction, Taguchi Method |
相關次數: | 點閱:278 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
本研究旨為透過機器學習(Machine Learning)應用於塑膠射出成形建立拉伸衝擊試片重量、產品Z軸翹曲及最低碳排放參數之預測。先以Moldex3D R16.0 進行模流分析,於半結晶性材料PP及非結晶性材料ABS的模擬結果探討重量及產品Z軸翹曲之趨勢並同時進行成形視窗實驗,其結果確立兩者材料之射出速度(Injection Velocity, Vinj)及熔膠溫度(Melt Temperature, Tmelt)。利用單一因子的實驗分析對試片重量最具影響的參數為背壓(Back Pressure, Bp),而翹曲則為射出速度(Vinj)、模具溫度(Mold Temperature, Tmold)、保壓壓力(Packing pressure, Ppacking)及冷卻時間(Cooling Time, tcooling),並將此參數作為田口方法(Taguchi Method)設計直交表進行實驗分析。運用類神經網路(Neural Network, NN),對試片重量、翹曲與碳排放量進行建立模型及預測,在重量方面兩者材料預測準確率皆達98 %以上,PP翹曲預測準確率達96 %,碳排放量準確率達77 %,ABS翹曲預測準確率達68 %,碳排放量準確率為66 %,在田口方法最佳參數分析中,將碳排放量於PP降低 13.3 % ,ABS降低34 %,顯示本研究對於碳排放最佳化之成果,經由本研究結合田口方法及類神經網路(Neural Network, NN)未來可於低碳製程及能量耗損之評估模式中應用。
This research focuses on predicting plastic product weight, warpage, and the lowest carbon emission parameter of tensile and impacts specimens through application of machine learning to injection molding process. At the same time, the forming window experiment is performed. Results establish the Injection Velocity (Vinj) and Melt Temperature (Tmelt) of the two plastic materials PP and ABS. The main effect factor of weight is Back Pressure (Bp) in a single factor experiment. However, the main effect factor of warpage includes the Injection Velocity (Vinj), Mold Temperature (Tmold), Packing Pressure (Ppacking), and Cooling Time (tcooling). Then these parameters are used by Taguchi Method to design orthogonal table for experimental analysis. Neural Network (NN) is used to model and predict the weight, warpage, and carbon emissions of the specimens. In terms of weight, the predicted accuracy of weight in PP and ABS both materials is more than 98 %, and the predicted warpage accuracy rate in PP material is 96 %, the prediction accuracy rate of carbon emission is 77 %, the prediction accuracy rate of ABS warpage is 68 %, and the carbon emission accuracy rate is 66 %. For the best parameter analysis of Taguchi Method, the carbon emission of PP can be reduced to 13.3 %, and ABS can be decreased to 34 %. Results show that the optimization of carbon emissions which combined with Taguchi method and Neural Network (NN) can be applied on the evaluation of low carbon processes and energy consumption for sustainable manufacturing in the future.
[1] 曾淑玲,"非球面塑膠鏡片收縮誤差補償之研究",碩士論文,機械工程系,國立臺灣科技大學,台北市,2005。
[2] D.-S. Choi and Y.-T. Im, "Prediction of shrinkage and warpage in consideration of residual stress in integrated simulation of injection molding", Composite Structures, vol. 47, no. 1-4, pp. 655-665, 1999.
[3] T. C. Chang and E. Faison III, "Shrinkage behavior and optimization of injection molded parts studied by the Taguchi method", Polymer Engineering & Science, vol. 41, no. 5, pp. 703-710, 2001.
[4] 刑玉璽,"射出成型之塑膠光學讀取透鏡收縮",碩士論文,航空太空工程學系碩博士班,國立成功大學,台南市,2003。
[5] 林炫良,"厚件產品保壓過程對於收縮率與殘留應力影響之研究," 中原大學機械工程研究所學位論文,pp. 1-68, 2003。
[6] K. Kwon, A. Isayev, and K. Kim, "Toward a viscoelastic modeling of anisotropic shrinkage in injection molding of amorphous polymers", Journal of Applied Polymer Science, vol. 98, no. 5, pp. 2300-2313, 2005.
[7] J. Pomerleau and B. Sanschagrin, "Injection molding shrinkage of PP: Experimental progress", Polymer Engineering & Science, vol. 46, no. 9, pp. 1275-1283, 2006.
[8] 張鮮文,"光學元件射出成形體積收縮與光學均勻性之研究",碩士論文,機械工程系,國立臺灣科技大學,台北市,2007。
[9] H. Hassan, "An experimental work on the effect of injection molding parameters on the cavity pressure and product weight", The International Journal of Advanced Manufacturing Technology, vol. 67, no. 1-4, pp. 675-686, 2013.
[10] 王立紘,"微振動式射出壓印成形於離軸非球面光柵元件之成形誤差分析研究",碩士論文,機械工程系,國立臺灣科技大學,台北市,2019。
[11] H. Lau, A. Ning, K. Pun, and K. Chin, "Neural networks for the dimensional control of molded parts based on a reverse process model", Journal of Materials Processing Technology, vol. 117, no. 1-2, pp. 89-96, 2001.
[12] M. Altan, "Reducing shrinkage in injection moldings via the Taguchi, ANOVA and neural network methods", Materials & Design, vol. 31, no. 1, pp. 599-604, 2010.
[13] P. Zhao, H. Zhou, Y. He, K. Cai, and J. Fu, "A nondestructive online method for monitoring the injection molding process by collecting and analyzing machine running data", The International Journal of Advanced Manufacturing Technology, vol. 72, no. 5-8, pp. 765-777, 2014.
[14] H. Tercan, A. Guajardo, J. Heinisch, T. Thiele, C. Hopmann, and T. Meisen, "Transfer-learning: Bridging the gap between real and simulation data for machine learning in injection molding", Procedia Cirp, vol. 72, pp. 185-190, 2018.
[15] 李宥增,"模擬退火法應用在離軸非球面光柵元件之成形誤差分析研究",碩士論文,機械工程系,國立臺灣科技大學,台北市, 2020。
[16] J. Jeswiet and S. Kara, "Carbon emissions and CES™ in manufacturing", CIRP annals, vol. 57, no. 1, pp. 17-20, 2008.
[17] C.-W. Park et al., "Energy consumption reduction technology in manufacturing—A selective review of policies, standards, and research", International journal of precision engineering and manufacturing, vol. 10, no. 5, pp. 151-173, 2009.
[18] 黃堯弘,"電泳沉積輔助線鋸切割於矽基板加工之永續性分析之研究",碩士論文,機械工程系,國立臺灣科技大學,台北市,2012。
[19] Q. Lu, G.-H. Zhou, C. Zhou, and Z.-D. Xiao, "A carbon emissions allocation method based on temperature field for products in the usage stage" ,The International Journal of Advanced Manufacturing Technology, vol. 91, no. 1-4, pp. 917-929, 2017.
[20] L. Korbelyiova, C. Malefors, C. Lalander, F. Wikström, and M. Eriksson, "Paper vs leaf: Carbon footprint of single-use plates made from renewable materials", Sustainable Production and Consumption, vol. 25, pp. 77-90, 2021.
[21] P. Matarrese, A. Fontana, M. Sorlini, L. Diviani, I. Specht, and A. Maggi, "Estimating energy consumption of injection moulding for environmental-driven mould design", Journal of Cleaner Production, vol. 168, pp. 1505-1512, 2017.
[22] 王晴遠,"高分子熔膠於彈臂搭接處之射出成形與分子配向性分析",碩士論文,機械工程系,國立臺灣科技大學,台北市,2010。
[23] S. Hattori, K. Nagato, T. Hamaguchi, and M. Nakao, "Rapid injection molding of high-aspect-ratio nanostructures", Microelectronic engineering, vol. 87, no. 5-8, pp. 1546-1549, 2010.
[24] 廖啓宏,"聚乳酸添加蠶砂複合材料於射出成形之機械性質與生物分解之研究",碩士論文,機械工程系,國立臺灣科技大學,台北市,2016。
[25] Moldex3D, "Moldex3D R15.0 Help", 2014.
[26] 陳炤彰,李瑞陽,游嘉瑋,李嘉誠,"塑膠射出成形模具設計與分析",五南出版,2017。
[27] 林政佑,"功能按鍵之彈臂斷面設計與射出成形最佳化",碩士論文,機械工程系,國立臺灣科技大學,台北市,2008。
[28] 陳永坤,"雙面微溝槽之薄件射出成形研究" ,碩士論文,機械工程系,國立臺灣科技大學,台北市,2005。
[29] W. S. McCulloch and W. Pitts, "A logical calculus of the ideas immanent in nervous activity", The bulletin of mathematical biophysics, vol. 5, no. 4, pp. 115-133, 1943.
[30] Z. Aram, S. Jafari, J. Ma, J. C. Sprott, S. Zendehrouh, and V.-T. Pham, "Using chaotic artificial neural networks to model memory in the brain", Communications in Nonlinear Science and Numerical Simulation, vol. 44, pp. 449-459, 2017.
[31] J. H. Jeon, S. S. Yang, and Y. J. Kang, "Estimation of sound absorption coefficient of layered fibrous material using artificial neural networks", Applied Acoustics, vol. 169, p. 107476, 2020.
[32] 經濟部工業局,"經濟部工業局產品環境足跡推動計畫",2021。
[33] 行政院環境保護署,"行政院環境保護署推動產品碳足跡管理要點",2020。
[34] United States Environmental Protection, Greenhouse Gas Emissions, 2021, Available from: https://www.epa.gov/ghgemissions/overview-greenhouse-gases.