| 研究生: |
顏靜良 Yan, Jing-Liang |
|---|---|
| 論文名稱: |
結合類神經田口法與基因演算法為基礎於冷軋板形製程參數最佳化之設計 Using Neural-Taguchi Method and Genetic Algorithm on Process Parameters Ptimization for Cold—Rolling Sheet Shape Control |
| 指導教授: |
林銘泉
Lin, Ming-Chyuan 蕭世文 Hsiao, Shih-Wen |
| 學位類別: |
碩士 Master |
| 系所名稱: |
規劃與設計學院 - 工業設計學系 Department of Industrial Design |
| 論文出版年: | 2011 |
| 畢業學年度: | 99 |
| 語文別: | 中文 |
| 論文頁數: | 83 |
| 中文關鍵詞: | 冷軋鋼捲 、板形 、田口實驗法 、類神經網路 、基因演算法 |
| 外文關鍵詞: | Cold-Rolling Coiling Steel, Sheet Shape, Taguchi Method, Neural Network Model, Genetic Algorithm |
| 相關次數: | 點閱:184 下載:7 |
| 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 |
由於軋延機的現代化,鋼捲於冷軋過程中,產出量逐年提高,如何提供設備正確的板形控制,以減少鋼捲於冷軋過程中不當損失而造成的剔退,以求能夠合於顧客要求之產品品質,儼然成為相關產業之重要課題。
本研究探討冷軋製程參數對鋼捲板形變異之影響,利用田口式實驗計劃法,以不同控制因子並藉由信號雜訊比(Signal to Noise Ratio)的改善分析,來蒐集並獲得最佳之製程參數,用來建構一適當的類神經網路模式,比較類神經網路方法是否能較傳統的統計技術,提供出較佳之結果。
研究最後應用基因演算法加以重整運算,來產生製程參數之最佳及最適值。加快收斂與類神經網路兩者間之最佳化求解,創造出滿足顧客需求的全方位產品,成為企業邁向科技化與現代化的最佳觸媒。
The output of coiling steel has increased year by year in the process of cold—rolling due to cold—rolled steel sheet mill advances.
It has become an important issue in related industries that provide the correct sheet shape control equipment, and reduce the coiling steel loss in the process of cold—rolling, in order to meet the custom requirements of product quality. In this study, we research the influence of cold-rolling control parameters to the coiling steel sheet shape variations. Using the Taguchi Method ,we analyze different control factors and Signal to Noise Ratio to collect the best control parameters to construct an appropriate Neural Network Model, and check that it can provide a better result than traditional statistical techniques.
Finally, The research use Genetic Algorithms and Recount to produce the best control parameters. Researching the optimal solution between control parameters and Neural Networks will create a full range of products and satisfy customers, as well as promote enterprises to move towards technology and modernization.
(一) 中文部分
田口玄一, 田口品質工程組譯,製造階段的品質工程,中國生產力 中心,台北,1989。
田口玄一,中國生產力中心譯,田口式品質工程概論,中國生產力中 心,台北,1990。
王文中,Excel於資料分析與統計學上的運用,博碩文化,台北,1997。
邱志洲、楊恭選、黃健生,應用類神經網路與田口直交法在氣體輔助射出成型製程中參數最佳化選擇之比較,輔仁管理評論,卷6,期1,頁163-180,1997。
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,台北,2003。
黎正中、陳源樹譯,Douglas C. Montromery著,實驗設計與分析,高立出版,台北,2003。
葉怡成,類神經網路模式應用與實作,儒林圖書有限公司,台北,1994。
葉怡成,類神經網路模式應用與實作(八版三刷),台北:儒林圖書有限公司,2004。
葉怡成,實驗計劃法-製程與產品最佳化,五南書局,台北,2005。
陳文欽、蔡志弘、劉康勇,應用類神經綱路於半導體氧化製程最佳化之研究,品質月刊,卷41,期6,頁70-76,2005。
郭良吉,第一熱軋軋輥研磨加工參數探討,中國鋼鐵股份有限公司技術與訓練季刊,卷30,期1,頁20-25,2005。
葉怡成,類神經網路模式應用與實作,儒林圖書公司,台北,2006。
江育民、黃建彰、賴正展,應用模糊理論與類神經網路於封膠製程品質之提升,工研院創新與科技管理研討會,2006。
余昭慶,應用類神經網路於電腦螢幕的文字與背景配色意象諮詢系統之發展,國立成功大學工業設計學系碩士論文,2008。
洪永祥、鄭淑萍、陳科淳,SMT 製程參數最佳化之分析,中華民國品質學會第12 屆全國品質研討會,CDROM,2006。
葉怡成、吳沛儒,基於類神經網路與交叉驗證法之田口方法,品質學報,卷16,期4,頁261-279,2009。
范揚志,應用類神經網路與基因演算法於射出成形製程參數最佳化之研究,私立中華大學科技管理研究所,碩士論文,1994。
郭育仁、廖啟銘、陳嘉暉、張銘昌,熱軋鉻鉬鋼軋入鬆脫銹皮坑改善,中國鋼鐵股份有限公司技術與訓練季刊,卷35,期1,頁25-33,2010。
羅華強,類神經網路-MATLAB 的應用,高立圖書有限公司,2006。
鍾易霖,應用類神經網路於顧客需求導向為基的參數化產品外形設計系統之發展,國立成功大學工業設計學系,碩士論文,2010。
(二) 英文部分
A. S. Khanna, “Introduction to High Temperature Oxidation and Corrosion,” ASM International, Vol. 4, pp.7-17, 2002.
B. H. Min, and B. C. Shin, “A Study on Volumetric Shrinkage of Injection Molded Parts Based on Neural Networks,” Journal of Injection Molding Technology, Vol. 5, Issue. 4, pp.201-207, 2001.
C. J. Wang, Y. C. Chang, “Formation and Growth Morphology of Nodules in the High-Temperature Oxidation of Fe-Mn-Al-C alloy,” Materials Chemistry and Physics, Vol. 77, pp.738-743, 2002
C. H. Wu, and W. S. Chen, “Injection Molding and Injection Compression Molding of Three-Beam Grating of DVD Pickup Lens,” Sensors & Actuators: A. Physical, Vol.125, Issue.2, pp.367-375, 2006.
George E. D. “Strengthening Mechanisms,” Mechanical Metallurgy, Vol. 84, No.5, pp.184-240, 2000.
Grima, M. Alvarez. and Bruines, P. A. and Verhoef, P. N. W. “Modeling Tunnel Boring Machine Performance by Neuro-Fuzzy Methods Tunnelling and Underground Space Technology,” Journal of Construction Engineering and Management , Vol. 15, No. 3, pp.259-269 ,2000.
Hsiao, S. W. and Huang, H.C., “A neural network based approach for product form design,” Design Studies, Vol.23, Issue 1, pp.67-84, 2002.
Khaw, John F. C., Lim, B. S. and Lim, Lennie E. N.,“Optimal Design of Neural Network Using the Taguchi method,” Neurocomputing, Vol. 7, Issue. 3, pp.225-245, 1995.
Lee, Jang Hee and Park, Sang Chan “Intelligent Profitable Customers Segmentation System Based on Business Intelligence Tools,” Expert Systems with Applications, Vol. 29, pp.145-152, 2005.
Rifat, Sonmez. and James, E. Rowing. “Construction Labor Productivity Modeling with Neural Networks,” Journal of Construction Engineering and Management, Vol. 124, No. 6, pp.498-504, 1998.
Tomoki Fukagawa, Hikaru Okada, Yasuhiro Maehara, “Mechanism of Red Scale Defect Formation in Si-Added Hot-Rolled Steel Sheets,” ISIJ International, Vol. 34, No. 11, pp. 906-911, 1994.
Tomoki Fukagawa, Hikaru Okada, Yasuhiro Maehara, “Effect of S on Hydraulic-Descaling-Ability in Si-added Hot-rolled Steel Sheets,” 鐵と鋼, Vol. 81, No. 5, pp. 84-109, 1995.
Tomoki Fukagawa, Hikaru Okada, Yasukiro Mashara, Hisao Fujikawa, “Effect of small amount of Ni on Hydraulic-Descaling-Ability in Si-Added Hot-Rolled Steel Sheets,” 鐵と鋼, Vol. 82, No. 1, pp. 16-39, 1996.
Tomoki Fukagawa, Hikaru Okada, Hisao Fujikawa, “Effect of P on Hydraulic-Descaling-Ability in Si Added Hot-Rolled Steel Sheets,” 鐵と鋼, Vol. 83, No. 5, pp.19-23, 1997.