跳到主要內容

臺灣博碩士論文加值系統

(100.26.176.111) 您好!臺灣時間:2024/07/16 14:35
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:蔡宜璋
研究生(外文):I-Chang Tsai
論文名稱:應用類神經網路與實驗設計法預測與優化射出成型試片之收縮率
論文名稱(外文):Shrinkage prediction of injection molded specimen by using artificial neural network and optimization with experimental design
指導教授:鍾禎元
指導教授(外文):Chen-Yuan Chung
學位類別:碩士
校院名稱:國立中央大學
系所名稱:機械工程學系
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2021
畢業學年度:110
語文別:中文
論文頁數:102
中文關鍵詞:收縮率田口方法反應曲面法倒傳遞網路遺傳演算法基底網路徑向基函數網路
外文關鍵詞:ShrinkageBack propagation network (BPN)Genetic algorithms of neural network (GANN)Radial basis function network (RBFN)Taguchi method (TM)Response surface methodology (RSM)
相關次數:
  • 被引用被引用:0
  • 點閱點閱:141
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
射出成型過程中的收縮是造成產品缺陷的原因之一,緣於高分子熔膠的流動特性使整個充填過程變得難以掌控,而溫度與壓力等參數的設定就是改善此問題的重點對策。傳統作法為透過經驗豐富的操作人員手動調整參數的方式,經過多次的試誤法(Trial and error)來找出適合的製程參數,除了仰賴操作員的經驗,也較缺乏嚴謹性與科學根據支撐。本研究利用模具型腔內的溫度與壓力感測器來監控成型時的熔膠狀態,將數據轉換成比容的形式來呈現成品品質,再透過實驗設計法結合類神經網路來預測並改善試片的成品品質,成品品質為體積收縮率與比容非均勻性的組合。實驗設計法使用田口方法與反應曲面法,類神經網路採用倒傳遞網路、遺傳演算法基底網路與徑向基函數網路,並比較各模型間的預測能力。首先經由田口方法之訊噪比篩選出顯著因子,再利用顯著因子進行反應曲面法之全因子實驗,得到一組最佳化製程參數與比容預測值,最後利用類神經網路的模型來驗證結果。
本研究透過實驗數據來建立製程參數與成品品質之模型,結果顯示,反應曲面法預測四組驗證範例之預測值與實驗值之平均驗證誤差為1.64%,且最佳化製程參數與中心點實驗相比改善了31.2%;倒傳遞網路預測值與實驗值之平均驗證誤差為5.49%;遺傳演算法基底網路預測值與實驗值之平均驗證誤差為8.42%;徑向基函數網路預測值與實驗值之平均驗證誤差為3.25%,顯示結合實驗設計法與類神經網路能有效的預測與改善射出成型之非線性問題。
Shrinkage is a reason that causes product defects in injection molding process, considering the flow behavior of the polymer melt makes the filling process difficult to control, which means the setting of parameter such as temperature and pressure is the key orientation to improve the problem. Traditionally, researchers can obtain the appropriate parameters set through trial and error method. However, relying on experience might cause the lack of rigorous, the experiment still needs a method with theoretical support. In this paper, temperature and pressure sensors in the mold cavity to monitor the melt state during molding process and collect data. Convert the data into specific volume to present as the quality of the product. Product quality represents the combination of volume shrinkage and non-uniformity of specific volume. Then combine the design of experiment (DOE) and artificial neural network (ANN) to predict and improve product quality. Taguchi method (TM) and response surface methodology (RSM) were used for design of experiment. Back propagation network (BPN), genetic algorithms of neural network (GANN) and radial basis function network (RBFN) were used for Ann. Next, discuss the pros and cons between these models. First, through signal to noise ratio (SNR) from Taguchi method to select the significant factors. Then use these factors to conduct the full factor experiment of response surface methodology, obtain a set of optimal process parameters and prediction value of specific volume. Finally, compare the experimental outcome with prediction value of the ANN model for validation.
In this paper, a model which contains process parameters and product quality constructed through experiment data finally shows the validation error rate of response surface methodology prediction of four validation dataset and value of experiment is 1.64 percent in average. And the prediction value of optimal parameter is improved by 31.2 percent compared to the center point experiment; validation error rate of back propagation network prediction and value of experiment is 5.49 percent in average; validation error rate of genetic algorithms of neural network prediction and value of experiment is 5.49 percent in average; validation error rate of radial basis function network prediction and value of experiment is 3.25 percent in average. The results show that the combination of design of experiment and artificial neural network is effectively on predicting and improving the nonlinear problem in injection molding.
摘要 i
Abstract iii
致謝 v
目錄 vi
圖目錄 ix
表目錄 xii
第1章、 緒論 1
1-1 前言 1
1-2 文獻回顧 2
1-3 研究動機與目的 5
1-4 研究流程 6
第2章、 基本原理與理論模式 8
2-1 射出成型比容狀態變化 8
2-2 翹曲與收縮預測方法 9
2-3 實驗設計法 11
2-3-1 田口方法 12
2-3-2 直交表 12
2-3-3 訊號雜訊比 13
2-3-4 變異分析 14
2-3-5 反應曲面法 15
2-3-6 迴歸分析 15
2-3-7 中央合成設計 16
2-4 類神經網路 17
2-4-1 倒傳遞網路 25
2-4-2 遺傳演算法基底網路 31
2-4-3 徑向基函數網路 34
2-4-4 網路品質評估指標 36
第3章、 研究方法 39
3-1 射出成型設備及溫度與壓力監視系統 39
3-2 模具介紹 47
3-3 材料介紹 47
3-4 實驗設計法 49
3-4-1 田口方法研究流程 49
3-4-2 反應曲面法研究流程 51
3-5 類神經網路實驗流程 53
3-5-1 Super PCNeuron 53
3-5-2 倒傳遞網路研究流程 54
3-5-3 田口方法優化倒傳遞網路 56
3-5-4 遺傳演算法基底網路研究流程 58
3-5-5 SIMULIA Isight 60
3-5-6 Wolfram Mathematica 60
3-5-7 徑向基函數網路研究流程 60
第4章、 結果與討論 65
4-1 田口方法結果 65
4-2 反應曲面法結果 68
4-3 預設倒傳遞網路與優化倒傳遞網路結果 70
4-4 遺傳演算法基底網路結果 75
4-5 徑向基函數網路結果 76
4-6 反應曲面法與類神經網路比較與探討 76
第5章、 結論與未來展望 78
5-1 結論 78
5-2 未來展望 79
參考文獻 81
[1]維基百科,自由的百科全書. 射出成型. Available: https://zh.wikipedia.org/wiki/%E6%B3%A8%E5%B0%84%E8%A3%BD%E6%A8%A1
[2]M. C. Huang and C. C. Tai, "The effective factors in the warpage problem of an injection-molded part with a thin shell feature," Journal of Materials Processing Technology, vol. 110, pp. 1-9, 2001.
[3]C. C. Chen, P. L. Su, and Y. C. Lin, "Analysis and modeling of effective parameters for dimension shrinkage variation of injection molded part with thin shell feature using response surface methodology," The International Journal of Advanced Manufacturing Technology, vol. 45, p. 1087, 2009.
[4]F. Rosenblatt, "The perceptron: a probabilistic model for information storage and organization in the brain," vol. 65, p. 386, 1958.
[5]P. Werbos, "Beyond regression : new tools for prediction and analysis in the behavioral sciences," PhD thesis, Harvard University, 1974.
[6]F. Yin, H. Mao, L. Hua, W. Guo, and M. Shu, "Back Propagation neural network modeling for warpage prediction and optimization of plastic products during injection molding," Materials & Design, vol. 32, pp. 1844-1850, 2011.
[7]W. C. Chen, P. H. Tai, M. W. Wang, W. J. Deng, and C. T. Chen, "A neural network-based approach for dynamic quality prediction in a plastic injection molding process," Expert Systems with Applications, vol. 35, pp. 843-849, 2008.
[8]劉信成, "應用多元迴歸與倒傳遞類神經網路預測企業獲利能力之研究," 碩士, 工業工程與工程管理學系碩士在職專班, 國立清華大學, 新竹市, 2018.
[9]J. H. Holland, Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT press, 1992.
[10]S. Najihah et al., "Analysis of Shrinkage on Thick Plate Part using Genetic Algorithm," in MATEC Web of Conferences, 2016, vol. 78, p. 01083: EDP Sciences.
[11]B. Ozcelik and T. Erzurumlu, "Determination of effecting dimensional parameters on warpage of thin shell plastic parts using integrated response surface method and genetic algorithm," International Communications in Heat and Mass Transfer, vol. 32, pp. 1085-1094, 2005.
[12]陳盈秀, "基因演算法自動演化類神經網路應用於衛星影像判釋與土砂災害評估模式之建置," 碩士, 土地管理與開發學系碩士班, 長榮大學, 台南市, 2010.
[13]D. S. Broomhead and D. Lowe, "Radial basis functions, multi-variable functional interpolation and adaptive networks," Royal Signals and Radar Establishment Malvern (United Kingdom)1988.
[14]S. Kitayama, K. Tamada, M. Takano, and S. J. T. I. J. o. A. M. T. Aiba, "Numerical and experimental investigation on process parameters optimization in plastic injection molding for weldlines reduction and clamping force minimization," vol. 97, pp. 2087-2098, 2018.
[15]張詠棨, "半徑基底函數(RBF)類神經網路應用於LED晶圓缺陷檢測," 碩士, 資訊工程研究所, 國立雲林科技大學, 雲林縣, 2006.
[16]莊至勛, "基於RBF神經網路之無縫超緊密GPS/INS導航系統設計," 通訊與導航工程學系, 國立臺灣海洋大學, 基隆市, 2012.
[17]B. Ozcelik and T. Erzurumlu, "Comparison of the warpage optimization in the plastic injection molding using ANOVA, neural network model and genetic algorithm," Journal of Materials Processing Technology, vol. 171, pp. 437-445, 2006.
[18]K. M. Tsai and H. J. Luo, "An inverse model for injection molding of optical lens using artificial neural network coupled with genetic algorithm," Journal of Intelligent Manufacturing, vol. 28, pp. 473-487, 2017.
[19]W. R. Jong, Y. M. Huang, Y. Z. Lin, S. C. Chen, and Y. W. Chen, "Integrating Taguchi method and artificial neural network to explore machine learning of computer aided engineering," Journal of the Chinese Institute of Engineers, vol. 43, no. 4, pp. 346-356, 2020/05/18 2020.
[20]施昭宏, "PEMFC性能仿真與其田口方法應用之研究," 碩士, 自動化工程系暨機電光系統研究所, 建國科技大學, 彰化縣, 2007.
[21]李偉正, "運用實驗設計和倒傳遞類神經網路結合模式於降低觸控玻璃製程阻抗之研究," 博士, 工業工程研究所, 中原大學, 桃園縣, 2014.
[22]科盛科技股份有限公司, 真實三維模流分析技術與應用. 科盛科技股份有限公司, 2016.
[23]王茂齡、張榮語和許嘉翔, 模流分析理論與實務. 科盛科技股份有限公司, 2018.
[24]S. Rogelj and M. Krajnc, "Pressure and temperature behavior of thermoplastic polymer melts during high‐pressure expansion injection molding," Polymer Engineering & Science, vol. 48, pp. 1815-1823, 09/01 2008.
[25]N. Stanciu, F. Stan, and C. Fetecau, "Melt Shear Rheology and pVT Behavior of Polypropylene / Multi-Walled Carbon Nanotube Composites," Materiale Plastice, vol. 55, pp. 482-487, 12/30 2018.
[26]R. Y. Chang, C. H. Chen, and K. S. Su, "Modifying the Tait equation with cooling-rate effects to predict the pressure-volume-temperature behaviors of amorphous polymers: modeling and experiments," Polymer Engineering and Science, Article vol. 36, p. 1789, 1996.
[27]行銷資料科學. (2021). 實驗設計法(Experimental Design Research). Available: https://medium.com/marketingdatascience/%E5%AF%A6%E9%A9%97%E8%A8%AD%E8%A8%88%E6%B3%95-experimental-design-research-3076122cfb1e
[28]永析統計. (2020). 信效度分析基本介紹. Available: https://www.yongxi-stat.com/reliability-validity-intro/
[29]維基百科,自由的百科全書. 訊號雜訊比. Available: https://zh.wikipedia.org/wiki/%E4%BF%A1%E5%99%AA%E6%AF%94
[30]李輝煌, 田口方法:品質設計的原理與實務. 高立圖書有限公司, 民97.
[31]維基百科,自由的百科全書. 響應曲面法. Available: https://zh.wikipedia.org/zh-tw/%E5%93%8D%E5%BA%94%E6%9B%B2%E9%9D%A2%E6%B3%95
[32]葉怡成, 實驗計畫法:製程與產品最佳化. 五南圖書出版股份有限公司, 2001.
[33]林李旺, 突破品質水準:實驗設計與田口方法之實務應用. 全華圖書股份有限公司, 2013.
[34]大和有話說. (2018). 完整解析AI人工智慧:3大浪潮+3大技術+3大應用. Available: https://dahetalk.com/2018/04/08/%E5%AE%8C%E6%95%B4%E8%A7%A3%E6%9E%90ai%E4%BA%BA%E5%B7%A5%E6%99%BA%E6%85%A7%EF%BC%9A3%E5%A4%A7%E6%B5%AA%E6%BD%AE%EF%BC%8B3%E5%A4%A7%E6%8A%80%E8%A1%93%EF%BC%8B3%E5%A4%A7%E6%87%89%E7%94%A8%EF%BD%9C/
[35]Q. Jarosz. (2009). 典型神經元的結構. Available: https://commons.wikimedia.org/w/index.php?curid=7616130
[36]葉怡成, 應用類神經網路. 儒林圖書有限公司, 民90.
[37]江衍銘, "二階段動態回饋式類神經網路於流量預測," 碩士, 生物環境系統工程學系暨研究所, 國立臺灣大學, 台北市, 2002.
[38]葉怡成, 類神經網路模式應用與實作. 儒林出版, 1993.
[39]TOWARDSDATASCIENCE.COM. (2021). Boost your Network Performance. Available: https://laptrinhx.com/boost-your-network-performance-1920317541/
[40]RBF and EBF Models. Available: https://abaqus-docs.mit.edu/2017/English/IhrUserMap/ihr-c-Reference-RBFandEBF.htm
[41]M. Hosoz, H. M. Ertunc, and H. Bulgurcu, "Performance prediction of a cooling tower using artificial neural network," Energy Conversion and Management, vol. 48, no. 4, pp. 1349-1359, 2007/04/01/ 2007.
[42]台中精機. 台中精機射出成型機規格資訊. Available: https://www.victortaichung.com/injection-machines/tw/vsp-60-e.htm
[43]潤輝科技有限公司. AO系列油式溫度控制機規格表. Available: http://www.a1-max.com.tw/t/pro_ao.htm#spec
[44]晏邦電機工業有限公司. 料斗乾燥機 (HD/IHD/DHD). Available: https://www.yannbang.com/hopper-dryer-tw
[45]双葉電子工業株式会社. 樹脂圧力計測システム. Available: http://www.futaba.co.jp/precision/mold_marshall/mps08s/index
[46]双葉電子工業株式会社. 樹脂温度計測システム. Available: http://www.futaba.co.jp/precision/mold_marshall/temperature/index
[47]龍成塑膠. (2019). 塑膠材質大補帖:塑膠ABS. Available: https://www.lcpf.com.tw/tw/knowledge/plastic-material/006?page=1&rtnKind=list
[48]葉怡成, 類神經網路模式應用與實作. 儒林圖書有限公司, 2003.
[49]陳耀茂和殷純淵, 類神經網路PCNeuron使用手冊. 鼎茂圖書出版股份有限公司: 邱昌其, 民93.
電子全文 電子全文(網際網路公開日期:20251201)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊