(3.238.130.97) 您好!臺灣時間:2021/05/09 03:43
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:::

: 
twitterline
研究生:吳瑞桓
研究生(外文):Jui-Huan Wu
論文名稱:觸控保護玻璃切割品質製程參數最佳化之研究
論文名稱(外文):A Study on Improving Touch Cover Glass Cutting Quality through Optimization of Process Parameters
指導教授:洪永祥洪永祥引用關係
指導教授(外文):Yung-Hsiang Hung
學位類別:碩士
校院名稱:國立勤益科技大學
系所名稱:工業工程與管理系
學門:工程學門
學類:工業工程學類
論文種類:學術論文
論文出版年:2013
畢業學年度:101
語文別:中文
論文頁數:71
中文關鍵詞:觸控面板田口品質工程保護玻璃類神經網路基因演算法
外文關鍵詞:Touch PanelTaguchi experimental designCover GlassArtificial Neural NetworksGenetic Algorithms
相關次數:
  • 被引用被引用:1
  • 點閱點閱:307
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:29
  • 收藏至我的研究室書目清單書目收藏:0
近年來3C產業的觸控面板需求大增,對於玻璃強度的品質更為重視,傳統玻璃切割上標準型刀輪(penett)常會造成嚴重裂紋等品質問題,讓中央裂紋深度會受限於側向裂紋的產生而無法持續增加,並須於劃線完後再進行裂片製程,缺點是會產生一種徑向裂紋使玻璃的彎曲強度大幅降低。有別於傳統切割方式,異型全切割(Full-Cut)的有齒型刀輪讓垂直裂紋浸透得比一般劃線裂片更深,可實現無破裂和分斷系統簡化現象,其特色是能使劃線後的玻璃自動裂開。本研究結合類神經網路預測模型對異型全切割觸控保護玻璃(Touch Cover Glass)的強度品質進行預測,並使用基因演算法優化類神經的權重值和偏壓值,藉此改善產品品質與玻璃強度。本研究使用了三種分析方法:田口品質工程、倒傳遞類神經網路及基因-倒傳遞類神經網路,並經過參數最佳化找出影響保護玻璃品質之組合後,基因-倒傳遞類神經網路可有效地減少製程生產週期,且有能力來改善觸控保護玻璃強度的品質使產能提昇,並可提供給工程人員進行製程參數調整的參考依據。
In recent years, the demand for touch panels on the 3C industry has greatly increased, thus, greater importance is attached to glass strength quality. The standard penett, a traditional glass cutting method, usually results in quality problems, such as severe cracking. The depth of a central crack cannot continue increasing due to lateral cracking, and the breaking process must be done after scribing. This method can produce radial cracking, which greatly reduces glass bending strength. Unlike the traditional cutting method, the Full-Cut indented penett can cause deeper penetration of vertical cracks than general scribing, thus, it simplifies the crack-free breaking system. Its advantage is that the glass cracks automatically after being scribed. In this study, the artificial neural network forecasting model is used to forecast the strength quality of the touch cover glass produced by the Full-Cut, and a genetic algorithm is applied to optimize the weight and bias values of the artificial neutral network, in order to improve product quality and glass strength. Three analytic methods are used in this study, namely the Taguchi experimental design, a back-propagation artificial neural network, and a gene-back-propagation artificial neural network. After determining the combinations affecting cover glass quality, through parameter optimization, the gene-back-propagation artificial neural network can effectively reduce the process cycle, improve touch cover glass strength quality and production capacity, and provide engineering personnel with a reference for the adjustment of process parameters.
摘要 i
Abstract ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 1
1.3 研究範圍與架構 2
1.4 研究流程架構 2
1.5 論文架構 4
第二章 文獻探討 5
2.1 觸控面板的發展及功能 5
2.2 田口品質工程 6
2.3 類神經網路 9
2.4 預測指標-根均方誤差 11
2.5 基因演算法理論 12
第三章 研究方法 14
3.1 研究方法與流程 14
3.2 實驗樣本整理 16
3.3 倒傳遞類神經網路 16
3.4 基因演算法 20
第四章 實例研究 24
4.1 實驗樣本介紹 24
4.2 田口品質工程分析 26
4.3 倒傳遞類神經網路分析 30
4.4 基因-倒傳遞類神經網路分析 33
4.4.1 實驗一(Original data, ORI) 34
4.4.2 實驗二(Standardized data, STD) 39
4.4.3 實驗三(All of the data repeated sampling, ADRS) 46
4.4.4 實驗四(Part of data repeated sampling, PDRS) 53
4.4.5 各種模式分析結果之比較 60
4.5 三種實驗分析比較 65
第五章 結論與建議 67
5.1 結論 67
5.2 未來研究方向 67
參考文獻 68

[1] 張斐章、張麗秋,2005,類神經網路,東華書局,台北。
[2] 蘇朝墩,2008,品質工程,三民書局,台北。
[3] 葉怡成,1997,應用類神經網路,儒林書局,台北。
[4] 周鵬程,2008,遺傳演算法原理與應用-活用Matlab第四版,全華科技圖書股份有限公司,台北。
[5] 洪銘峻,2009,以情境分析法來分析未來五年無線通訊技術(WiMAX)結合液晶觸控螢幕應用產品之發展,國立交通大學,碩士論文。
[6] 朱崇玄,2009,台灣電容式觸控面板產業之策略分析,國立交通大學,碩士論文。
[7] 林崇功,2011,台灣觸控面板產業經營策略探討-以M公司為例,東海大學,在職專班碩士論文。
[8] 吳文生,2009,導入綠色製程對觸控面板產業的影響研究 -以X公司為例,中原大學,碩士論文。
[9] 葉晉廷,2011,觸控面板黃光製程出貨品質提昇研究,逢甲大學,在職專班碩士論文。
[10] 劉佳營,2010,運用田口法進行安全眼鏡之塑膠射出成型參數最佳化,南台科技大學,碩士論文。
[11] 廖永富,2011,應用田口方法分析鈦合金切削之表面粗糙度與參數最佳化,逢甲大學,碩士論文。
[12] 陳柏光,2009,應用田口法探討銲線製程參數最佳化,逢甲大學,碩士論文。
[13] 龔彥勳,2012,CUDA之實數型遺傳演算法於多自由度機械臂的運動規劃,國立台北科技大學,碩士論文。
[14] 鄭書甫,2011,基因演算法與類神經網路在財務危機預測上之應用,長榮大學,碩士論文。
[15] 陳適宜,2010,基因類神經網路在臺股指數期貨的預測與蝶式交易策略研究,國立台北大學,碩士論文。
[16] Abed, M. A., Ismail, A. N., Hazi, Z. M., 2010, “Pattern recognition using genetic algorithm”, International Journal of Computer and Electrical Engineering, vol.2, pp.583-588.
[17] Aguir, H., BelHadjSalah, H., Hambli, R., 2010,“Parameter identification of an elasto-plastic behaviour using artificialneural networks–genetic algorithm method” , Materials and Design, vol. 32, issue 1, pp. 48-53.
[18] Ahmadzadeh, M., Fard, H. A., Saranjam, B., Salimi, H. R., 2012, “Prediction of residual stresses in gas arc welding by back propagation neural network”, NDT&;E International, vol. 52, pp. 136-143.
[19] Aryanezhad, M. B., Hemati M., 2008, “A new genetic algorithm for solving nonconvex nonlinear programming problems”, Applied Mathematics and Computation, vol.199, issue 1, pp.186–194.
[20] Ballantyne, K.N., Oorschot, R. A., Mitchell, R.J., 2008, “Reduce optimization time and effort: Taguchi experimental design methods”, Forensic Science International: Genetics Supplement Series, vol. 1, issue 1, pp.7-8.
[21] Corriveau, G., Guilbault, R., Tahan, A., 2010, “Genetic algorithms and finite element coupling for mechanical optimization”, Advances in Engineering Software, vol.41, issue3, pp.422–426.
[22] Dehuri, S., Roy, R., Cho, S.B., Ghosh, A., 2012, “An improved swarm optimized functional link artificial neural network (ISO-FLANN) for classification”, Journal of Systems and Software, vol. 85, issue6, pp. 1333-1345.
[23] Dubey, A. K., Yadava, V., 2008, “Multi-objective optimization of laser beam cutting process,” Optic &; Laser Technology, vol. 40, pp. 562–570.
[24] Dubey, A. K., Yadava, 2008, “Multi-objective optimization of Nd:YAG laser cutting of nickel-based superalloy sheet using orthogonal array with principal component analysis,” Optic &; Laser in Engineering, vol. 46, pp. 124–132.
[25] Kim, K. R., Kim, J. H., Farson, D. F., Choi, H. W., Kim, K. H., 2008 ,“Hybrid laser cutting for flat panel display glass,” Japanese Journal of Application Physics, vol. 47, pp. 6978–6981.
[26] Li, H., Hu, C. X., Li, Y., 2012, “Application of the Purification of Materials Based on GA-BP”, Energy Procedia, vol. 17, pp. 762-769.
[27] Lin, H. C., Su, C. T., Wang, C. C., Chang, B. H., Juang, R. C., 2012,“Parameter optimization of continuous sputtering process based on Taguchi methods, neural networks, desirability function, and genetic algorithms”Expert Systems with Applications, vol. 39, pp. 12918-12925.
[28] Mantzaris, D., Anastassopoulos, G., Adamopoulos, A., 2011,“Genetic algorithm pruning of probabilistic neural networks in medical disease estimation”, Neural Networks, vol.24, issue 8, pp. 831-835.
[29] Orkcu, H. H., Bal, H., 2011,“Comparing performances of backpropagation and genetic algorithms in the data classification”, Expert Systems with Applications, vol. 38, issue 4, pp. 3703-3709.
[30] Pasandideh, S. H. R., Niaki, S. T. A., Nia, A. R., 2010, “A genetic algorithm for vendor managed inventory control system of multi-product multi-constraint economic order quantity model”, Expert Systems with Applications, vol. 38, issue 33, pp.2708-2716.
[31] Sedki, A., Ouazar, D., Mazoudi, E. E., 2009, “Evolving neural network using real coded genetic algorithm for daily rainfall–runoff forecasting” ,Expert Systems with Applications, vol. 36, issue 3, pp.4523-4527.
[32] Sohrabi, M. R., Jamshidi, S., Esmaeilifar, A., 2012, “Cloud point extraction for determination of Diazinon Optimization of the effective parameters using Taguchi method”, Chemometrics and Intelligent Laboratory Systems, vol. 110, pp. 49-54.
[33] Su, C. T., Hsiao, Y. H. and Chang, C. C., 2012, “Parameter Optimization Design for Touch Panel Laser Cutting Process”, IEEE Transactions on Automation Science and Engineering, vol. 9, pp. 320-329.
[34] Toledo, C. F. M., Franca, P. M., Morabito, R., Kimms, A., 2009, “Multi-population genetic algorithm to solve the synchronized and integrated two-level lot sizing and scheduling problem”, International Journal of Production Research, vol.47, pp.3097-3119.
[35] Tsai, C. H., Huang, B. W., 2008, “Diamond scribing and laser breaking for LCD glass substrates”, Journal of Materials Processing Technology ,vol. 198, issue1-3, pp. 350–358.
[36] Tsai, M. J., Li, C. H., Chen, C. C., 2008, “Optimal laser-cutting parameters for QFN packages by using artificial neural networks and genetic algorithm”, Journal of Materials Processing Technology, vol. 208, issue1-3, pp. 270–283.
[37] Wang, K. J., Wang, S. M., Chen, J. C., 2008, “A Resource Portfolio Planning Model Using Sampling-Based Stochastic Programming and Genetic Algorithm”, European Journal of Operational Research, vol. 184, issue 1, pp.327-340.
[38] Wu, J. Y., 2011, “MIMO CMAC neural network classifier for solving classification problems”, Applied Soft Computing, vol. 11, issue 2, pp. 2326-2333.
[39] Xie, Z., Zhang, Y., Jin, C., 2012, “Prediction of Coal Spontaneous Combustion in Goaf Based on the BP Neural Network”, Procedia Engineering, vol. 43, pp. 88-92.
[40] Yu, J., Xi, L., Zhou, X., 2009,“Identifying source(s) of out-of-control signals in multivariate manufacturing processes using selective neural network ensemble”, Engineering Applications of Artificial Intelligence, vol. 22,issue 1, pp.141-152.

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
系統版面圖檔 系統版面圖檔