隨著製造技術不斷進步，在消費市場中產品品質與成本逐漸受到重視，對於台灣為數眾多的中小企業而言，為經濟地提升產品品質，企業必須徹底理解生產系統之缺陷並加以修正，以降低失誤風險以及避免不必要的成本浪費，而品質工程方法則能滿足此項需求。品質工程方法為一系列線上及線外的品管方法來達到高品質水準目標，且各式各樣的品質工程方法已被應用在許多種不同行業並獲得顯著的成效。
精密鑄造為一種金屬加工技藝，因其表面精度高且能製造複雜幾何外型之特色而聞名。精密鑄造可應用範圍極廣，但因其製程容易受外在環境影響，故產品容易出現多種不同瑕疵，其中又以來源廣泛的砂孔缺陷最為棘手。傳統上因砂孔缺陷成因極為複雜，故生產方大多以消極的補救措施進行應對，但這也大幅增加生產成本以及週期，使得許多中小規模的精密鑄造廠無力提升自身競爭力。
本研究透過與個案公司的合作，將田口式品質工程方法以及計算智能方法應用於精密鑄造業中的砂孔缺陷改善。透過適當的實驗發現顯著影響砂孔缺陷的製造參數並透過兩種方法計算出最佳參數設定，經過確認實驗後確認改善後的參數設定能減少超過一半的砂孔缺陷，且大幅降低了個案公司的勞力成本以及生產週期，同時也提升個案公司之市場競爭力。

With the development of the manufacturing technology, the quality and the cost become more and more important to customers. For small and medium enterprises, they need to clarify their manufacturing system’s weakness completely to reduce the manufacturing cost and enhance their product’s quality in an economical way, and quality engineering methods could be a good tool to fulfill this need. Quality engineering are a series of methods to achieve a high quality level. Quality engineering methods have been implemented into different industries and was also confirmed to be the effective quality improvement tools.
Investment casting is a metal forming technique which is well-known for its ability to produce smooth surface and complicated geometric casting. The weakness of investment casting is it can be influenced by manufacturing environment easily, which the various defects may possibly occur. Sand inclusion is one of the most critical issues due to it’s various source.
To help investment casting industry to reduce the sand inclusion defect, two quality engineering methods – Taguchi Methods and Computational Intelligence Methods were used in this research to perform the process parameter optimization. By cooperating with a small investment casting factoring, a real experiment was conducted, and bring out an optimal setting for process parameter to reduce more than 50% defects.

摘要 I
Abstract II
致謝 III
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 研究架構 3
第二章 文獻探討 4
2.1 鑄造技術 4
2.1.1 精密鑄造技術 5
2.1.2 精密鑄造之砂孔問題 6
2.2 田口式品質工程 8
2.2.1 直交表 11
2.2.2 信號雜音比 12
2.2.3變異數分析 14
2.2.4確認實驗 15
2.2.5 參數設計 16
2.3 計算智能方法 18
2.3.1 類神經網路 19
2.3.2 基因演算法 23
2.3.3結合類神經演算法和基因演算法於參數設計之應用 25
第三章 研究方法 27
3.1 品質特性之定義 28
3.2 實驗因子 28
3.3 實驗設計架構 29
3.4 實驗數據分析、最佳化及確認實驗 31
3.4.1 信號雜音比之選用 31
3.4.2 田口方法之最佳化 31
3.4.3 計算智能方法之最佳化 32
3.4.4 確認實驗 32
第四章 研究結果 34
4.1田口方法最佳化結果 34
4.2計算智能方法最佳化結果 37
4.3 確認實驗 40
4.4改善成效與比較 41
第五章 結論 44
5.1結論 44
5.2未來研究方向 45
參考文獻 46

[1] 余豐榮，莊銘國，& 施啟順 (2007). 以田口方法提升鑄件品質之研究. 鑄造工程學刊， 33(4)， 17-24.
[2] 林文和 & 邱傳聖(1990)，鑄造學，高立圖書有限公司
[3] 林宗獻(2012)，精密鑄造學，全華圖書股份有限公司
[4] 蘇木春, & 張孝德. (1997). 機器學習: 類神經網路, 模糊系統以及基因演算法則. 全華科技圖書, 民國八十八年.
[5] 蘇朝墩 (2013)，品質工程：線外方法與應用，前程文化事業有限公司
[6] Alonso, J. M., Alvarruiz, F., Desantes, J. M., Hernández, L., Hernández, V., & Molto, G. (2007). Combining neural networks and genetic algorithms to predict and reduce diesel engine emissions. IEEE Transactions on Evolutionary Computation, 11(1), 46-55.
[7] Burke, L. I. (1991). Introduction to artificial neural systems for pattern recognition. Computers & Operations Research, 18(2), 211-220.
[8] Chou, C. J., & Chen, L. F. (2012). Combining neural networks and genetic algorithms for optimising the parameter design of the inter-metal dielectric process. International Journal of Production Research, 50(7), 1905-1916.
[9] Di Foggia, M., & D’Addona, D. M. (2013). Identification of critical key parameters and their impact to zero-defect manufacturing in the investment casting process. Procedia CIRP, 12, 264-269.
[10] Fausett, L. V. (1994). Fundamentals of neural networks. Prentice-Hall.
[11] Ghani, J. A., Choudhury, I. A., & Hassan, H. H. (2004). Application of Taguchi method in the optimization of end milling parameters. Journal of materials processing technology, 145(1), 84-92.
[12] Han, J., Pei, J., & Kamber, M. (2011). Data mining: concepts and techniques. Elsevier.
[13] Haykin, S. (1999). Neural networks: a comprehensive foundation, edition 2, 1999.
[14] Kacker, R. N., Lagergren, E. S., & Filliben, J. J. (1991). Taguchi’s orthogonal arrays are classical designs of experiments. Journal of research of the National Institute of Standards and Technology, 96(5), 577-591.
[15] Nalbant, M., Gökkaya, H., & Sur, G. (2007). Application of Taguchi method in the optimization of cutting parameters for surface roughness in turning. Materials & design, 28(4), 1379-1385.
[16] Pattnaik, S., Karunakar, D. B., & Jha, P. K. (2012). Developments in investment casting process—a review. Journal of Materials Processing Technology, 212(11), 2332-2348.
[17] Phadke, M. S. (1995). Quality engineering using robust design. Prentice Hall PTR.
[18] Taguchi, G. (1986). Introduction to quality engineering: designing quality into products and processes.
[19] Taguchi, G., Chowdhury, S., & Wu, Y. (2005). Taguchi's quality engineering handbook. Wiley.
[20] Tang, S. H., Tan, Y. J., Sapuan, S. M., Sulaiman, S., Ismail, N., & Samin, R. (2007). The use of Taguchi method in the design of plastic injection mould for reducing warpage. Journal of Materials Processing Technology, 182(1), 418-426.
[21] Yin, F., Mao, H., & Hua, L. (2011). A hybrid of back propagation neural network and genetic algorithm for optimization of injection molding process parameters. Materials & Design, 32(6), 3457-3464.
[22] Wu, Y., & Wu, A. (2000). Taguchi methods for robust design. American Society of Mechanical Engineers.