臺灣博碩士論文加值系統

鋁合金與鎂合金因為比重輕、硬度高、散熱性佳和能阻擋電磁干擾等多項特性，在現代工業與電子科技產業迅速蓬勃發中扮演著重要的應用材料，尤其是在汽車工業與電子產業方面，為了車體與3C(Computer、Communication、Consumer Electronics Products)產品的輕量化，採用鋁合金與鎂合金的接合就非常重要。
本研究為5052鋁合金和AZ31B鎂合金異種銲接之參數最佳化，以田口方法進行惰性氣體鎢極電弧銲接實驗，經由文獻探討與專家建議，選定銲道正面厚度、銲道寬度、銲道硬度、衝擊試驗和拉伸試驗則做為品質特性，透過特性要因圖決定銲接電流、銲接移行速度、鎢棒伸出量、鎢棒與母材間隙以及氬氣流量做為銲接參數。所得實驗數據運用S/N比和變異數分析結合的交叉法、TOPSIS、倒傳遞類神經網路模擬與基因演算法，找出異種銲接鋁合金與鎂合金最佳參數水準組合。
得到結果為銲接移行速度為影響品質特性最重要的參數。

Because of lightweight, high hardness, good heat dissipation and electromagnetic shielding characteristic, and so on, aluminum alloy and magnesium alloy play an important applied material in the industry of modern and electronic technology in rapidly growing, especially in the aspect of automobile and electronic sectors. For lightweight automobile body and hi-tech products, it is very important to adopt the welding between aluminum alloy and magnesium alloy.
This study presents the optimal welding parameters of heterogeneous metal in 5052 aluminum alloy and AZ31B magnesium alloy, adopting Taguchi Method to take an experiment of gas tungsten arc welding. Literature review and expert advice determine that the quality characteristics are frontal thickness of the welded part, bead width, rockwell hardness, impact and tensile. Welding current, moving speed, protruding length of tungsten rod, the distance between tungsten rod and plate and the flow rate of argon gas are chosen to be used as the parameters by Causes & Effects Diagram. The measured data after the cross table combined signal-to-noise ratio and ANOVA, TOPSIS, back-propagation neural network simulation and genetic algorithm determine the best welding parameter levels combination for the heterogeneous metal in aluminum alloy and magnesium alloy.
The results show that the moving speed is the most important parameter affecting the quality characteristic.

誌謝 I
摘要 II
Abstract III
目錄 IV
圖目錄 VII
表目錄 VIII
第一章 緒論 1
1-1 研究背景與動機 1
1-2 研究目的 4
1-3 研究對象與範圍限制 4
1-4 研究流程 5
第二章 文獻探討 8
2-1 5052鋁合金 8
2-2 AZ31B鎂合金 10
2-3 惰氣鎢極電弧銲 12
2-4 異種銲接 14
2-5 田口與多重品質特性 20
2-6 類神經網路 21
2-7 基因演算法 23
第三章 研究方法 26
3-1田口方法 27
3-2理想解類似度順序偏好法 28
3-3倒傳遞類神經網路 31
3-4類神經網路結合遺傳基因演算法 36
第四章 實驗流程 40
4-1實驗材料 40
4-2實驗設備與銲接流程步驟介紹 41
4-3銲接品質特性之選定 44
4-4影響銲接品質特性之要因分析 48
4-5銲接參數的選擇 50
4-6配置田口方法直交法 52
第五章 實驗結果數據分析 55
5-1 銲接實驗與變異數分析 55
5-2 銲接實驗TOPSIS分析 64
5-3倒傳遞類神經網路分析 72
5-4基因演算法最佳化分析 74
5-5信賴區間分析 75
5-6驗證實驗 77
5-7最佳製程參數組合 78
第六章 結論與建議 79
6-1 結論 79
6-2 建議 80
參考文獻 81
中文部分 81
英文部分 83

中文部分
王恒、劉黎明、柳緒靜(2005)，鎂鋁異種材料TIG銲接接頭擴散行為分析，銲接學報，26(7)，5-8。
王春和(2001)，應用灰關聯分析法於多品質特性與等級類別品質特性之最佳化，交通大學工業工程與管理系博士論文。
王祝堂、田榮璋(2000)，鋁合金及其加工手冊，長沙：中南大學出版社，232-250。
王進德、蕭大全(2003)，類神經網路與模糊控制理論入門，台北：全華科技圖書。
任志遠、張燕、金丹萍、呂波(2013)，5052鋁合金薄板摩擦攪拌銲接頭組織和力學性能研究，熱加工工藝，5，185-187。
吳小俊、王懷建、白莉(2013)，AZ31B鎂合金薄板交流TIG銲接接頭組織和性能研究，兵器材料科學與工程，36(3)，66-68。
吳復強(2002)，田口品質工程，新北市：全威圖書，1-2。
吳濤、田鵬(2007)，銅與鋼的異種材料擴散銲接技術，黑龍江冶金，7，30-32、42。
李宏義(2015)，銲接電流變化對鎂合金TIG銲接的影響，電銲機，45(2)，105-107、111。
李隆盛(1990)，銲接實習，新北：全華科技圖書。
周長彬、蔡丕椿、郭央諶(2001)，銲接學，台北市：全華科技圖書，48。
柳緒靜、劉黎明、王恒、宋剛(2005)，鎂鋁異種金屬激光-TIG複合熱源銲銲接性分析，銲接學報，8，31-34。
胡庭睿(2015)，應用類神經網路與基因演算法於鎂合金薄板銲接參數最佳化之研究，華梵大學工業工程與經營資訊學系碩士論文。
殷春喜，黃軍慶，熊震東、賈翠催（2011），鋁及鋁合金 TIG 銲接特 性，金屬鑄鍛銲技術，(1)，1-4。
馬廣超、林三寶、宋建岭、楊春利、余翔、邵琳(2008)，5052鋁合金薄板攪拌摩擦銲工藝，銲接，10，39-42。
張志平、劉孝先(2014)，應用柔性演算法於航太鋁合金銲接參數最佳化之研究，品質學報，21(3)，205-216。
張忠樸(2005)，實驗設計速學活用法，台北：電路板資訊雜誌社，88。
張斐章、張麗秋(2005)，類神經，台北：東華書局。
梁國俐、苑少強(2008)，AZ31B鎂合金TIG銲接過程組織分析，唐山學院學報，21(2)，9-10、18。
陸志鴻(1982)，金屬材料測試法，新北:正中書局。
葉怡成(2009)，類神經網路模式應用與實作第九版，台北：儒林出版社。
鄧振源(2012)，多準則決策分析-方法與應用，台北：鼎茂圖書。
賴耿陽(1997)，薄鋼板軟鋼熔接技術，台南：復漢出版社
賴耿陽(1997)，薄鋼板軟鋼熔接技術，台南：復漢出版社。
羅乾(2010)，Cu/Al合金異種材料複合管電阻壓銲接頭連接特性分析，熱加工工藝，7，115-116、119。
蘇木春、張孝德(2003)，機器學習：類神經網路、模擬系統以及基因演算法則，台北市：全華科技圖書，9，2。
蘇州大學激光加工中心(2016)，玻璃與金屬銲接之異種銲接，取自(retrieved from) 2016/08/04，http://www.laserfair.com/news/201608/03/61427.html
蘇昭安(2003)，應用倒傳遞類神經網路在颱風波浪預報之研究，國立台灣大學工程科學與海洋工程學系碩士論文。
蘇朝墩(2008)，品質工程，台北：中華民國品質學會。
英文部分
Afrin, N., Chen, D.L., Cao, X., & Jahazi, M. (2008), Microstructure and Tensile Properties of Friction Stir Welded AZ31B Magnesium Alloy, Materials Science and Engineering: A, 472(1.2), 179-186.
Borrisutthekul, R., Miyashita, Y., & Mutoh, Y. (2005), Dissimilar Material Laser Welding between Magnesium Alloy AZ31B and Aluminum Alloy A5052-O, Science and Technology of Advanced Materials, 6(2), 199-204.
Canyurt, O.E., Kim, H.R., & Lee, K.Y. (2008), Estimation of Laser Hybrid Welded Joint Strength by using Genetic Algorithm Approach, Mechanics of Materials, 40(10), 825-831.
Esme, U., Bayramoglu, M., Kazancoglu, Y. & Ozgun, S. (2009), Optimization of Weld Bead Geometry in TIG Welding Process using Grey Relation, Materials and Technology, 43(3), 143-149.
Hamedi, M., Shariatpanahi, M., & Mansourzadeh, A. (2007), Optimizing Spot Welding Parameters in a Sheet Metal Assembly by Neural Networks and Genetic Algorithm, Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 221(7), 1175-1184.
Jeyapaul, R., Shahabudeen, P., & Krishnaiah, K. (2005), Quality Management Research by Considering Multi-response Problems in the Taguchi Method–a review, The International Journal of Advanced Manufacturing Technology, 26(11-12), 1331-1337.
Know, Y.J., Shigematsu, I., & Saito, N. (2008), Dissimilar Friction Stir Welding between Magnesium and Aluminum Alloys, Materials Letters, 62(23), 3827-3829.
Kramer, L.S., & Pickens, J.R. (1992), Microstructure and Properties of a Welded Al-Cu-Li Alloy, Supplement to the Welding Journal, April, 115-s to 121-s.
Kumar, A., & Sundarrajan, S. (2009), Optimization of Pulsed TIG Welding Process Parameters on Mechanical Properties of AA 5456 Aluminum Alloy Weldments, Materials & Design, 30(4), 1288-1297.
Kwon,Y.J., Shim, S.B., & Park, D.H. (2009), Friction Stir Welding of 5052 Aluminum Alloy Plates, Transactions of Nonferrous Metals Society of China, 19(1), s23-s27.
Law, R. (2000), Back-propagation Learning in Improving the Accuracy of Neural Network-based Tourism Demand Forecasting, Tourism Management, 21(4), 331-340.
Liao, Y.G. (2005), Optimal Design of Weld Pattern in Sheet Metal Assembly Based on a Genetic Algorithm, The International Journal of Advanced Manufacturing Technology, 26(5), 512-516.
Liu, L.M., Zhang, Z.D., Liu, F., Wang, Z., & Wang, H.Y. (2013), Effect of addition of Ce in Sn-30Zn Solder on the Structure and Properties of the Mg/Al-brazed Joint, Journal of Materials Science, 48, 2030-3037.
Liu, L.M., Zhao, L.M., & Xu, R.Z. (2009), Effect of Interlayer Composition on the Microstructure and Strength of Diffusion Bonded Mg/Al Joint, Materials & Design, 30(11), 4548-4551.
Magudeeswaran, G., Nair, S. R., Sundar, L. & Harikannan, N. (2014), Optimization of Process Parameters of the Activated Tungsten Inert Gas Welding for Aspect Ratio of UNS S32205 Duplex Stainless Steel Welds, Defence Technology, 10(3), 251-260.
Manikya Kanti, K., & Srinivasa Rao, P. (2008), Prediction of Bead Geometry in Pulsed GMA Welding using Back Propagation Neural Network, Journal of Materials Processing Technology, 200(1-3), 300-305.
Metal Suppliers Online(2016a), 5052 Aluminum Material Property Data Sheet - Product Availability and Request a Quote, retrieved from 2016/08/13 http://www.suppliersonline.com/propertypages/5052.asp#chemistry
Metal Suppliers Online(2016b), AZ31B Magnesium Alloys Material Property Data Sheet - Product Availability and Request a Quote, retrieved from 2016/08/13 http://www.suppliersonline.com/propertypages/AZ31B.asp#chemistry
Mitchell, M. (1998), An Introduction to Genetic Algorithms, 1, 2-3.
Nagesh, D.S. & Datta, G.L. (2002), Prediction of Weld Bead Geometry and Penetration in Shielded Metal-arc Welding using Artificial Neural Networks, Journal of Materials Processing Technology, 123(2), 303-312.
Okuyucu, H., & Kurt, A. (2007), Artificial Neural Network Application to the Friction Stir Welding of Aluminum Plates, Materials & Design, 28(1), 78-84.
Pal, S., Pal, S.K., & Samantaray, A.K. (2008), Artificial Neural Network Modeling of Weld Joint Strength Prediction of a Pulsed Metal Inert gas Welding Process using Arc Signals, Journal of Materials Processing Technology, 202(1-3), 464-474.
Rathod, M.J., & Kutsuna, M. (2004), Joining of Aluminum Alloy 5052 and Low-Carbon Steel by Laser Roll Welding, Welding Research, 83(1),16S-26S.
Sathiya, P., Panneerselvan, K., & Jaleel, M.Y.A. (2012), Optimization of Laser Welding Process Parameters for Super Austenitic Stainless Steel using Artificial Neural Networks and Genetic Algorithm, Materials & Design, 36, 490-498.
Sato, Y.S., Park, S.H.C., Michiuchi, M., & Kokawa, H. (2004), Constitutional Liquation during Dissimilar Friction Stir Welding of Al and Mg Alloys, Scripta Materialia, 50(9), 1233-1236.
Taguchi, G. (1986), Introduction to quality engineering: designing quality into products and processes, Asian Productivity Organization, Tokyo.
Tomg, L. I., & Su, C. T. (1997), Optimizing Multi-Response Problems in the Taguchi Method by Fuzzy Multiple Attribute Decision Making, Quality and Reliability Eng. Int’l, 13, 25-34.
Wang, X.H., Wang, K.S., Shen, Y., & Hu, K. (2008), Comparison of Fatigue Property between Friction Stir and TIG Welds, International Journal of Minerals, Metallurgy and Materials, 15(3), 280-284.
Wang, Z., Wang, H.Y., & Liu, L.M. (2012), Study on Low Temperature Brazing of Magnesium Alloy to Aluminum Alloy Using Sn-xZn Solders, Materials & Design, 39, 14-19.
Yan, Y., Zhang, D.T., Qiu, C., & Zhang, W. (2010), Dissimilar Friction Stir Welding between 5052 Aluminum Alloy and AZ31 Magnesium Alloy, Transactions of Nonferrous Metals Society of China, 20(2), 619-623.
Yoon, K., & Hwang, C.L. (1981), Multiple Attribute Decision Making–Methods and Applications, New York: Springer-Verlag.
Yu, S.R., Chen, X.J., & Liu, Y.H. (2009), Process Optimization of Friction Stir Welding of AZ31B Magnesium Alloy, Hot Working Technology, 38(15), 88-89.
Zhang, H.T., & Song, J.Q. (2011), Microstructural Evolution of Aluminum Magnesium Lap Joints Welded using MIG Process with Zinc Foil as an Interlayer, Materials Letters, 65, 3292-3294.
Zhang, Y.H., Ding, J.H., & Wang, X.J. (2009), Microstructure and Mechanical Properties of Friction Stir Welding Joint for Mg Alloy AZ31B, Hot Working Technology, 38(9), 106-108.
Zhang, Z.H., Yang, X.Q., Zhang, J.L., Zhou, G., Zhou, G., Xu, X.D., & Zou, B.L. (2011), Effect of Welding Parameters on Microstructure and Mechanical Properties of Friction Stir Spot Welded 5052 Aluminum Alloy, Materials & Design, 32(8.9), 4461-4470.