隨著科技不斷的進步創新，許多產業為了提升生產工作效率，近年來許多企業也不斷改變自我生產模式，從原本的自動化生產慢慢演變導向智慧製造生產，因應許多國家所面臨經驗技術員人口老化等因素，在本研究目標是優化智慧機械設備能夠及時預測輪盤磨損，並主要針對研磨焊道加工金屬基複合材料所造成的研磨輪盤磨耗影響組合，應用田口方法作為實驗設計（DOE）來優化研磨加工過程中所產生的因子包含：研磨耗材、進幾率、轉速及機台施力之間的影響關係，所回饋受力值的參數，藉由運用田口方法以品質特性望小為成型過程相關作為目標函數在有限的元件模擬當中，並透過L9直交表配合實驗設計參數組合獲得最佳研磨條件，已盡量減少實驗運行次數並提高實驗結果的可靠性，與運用類神經網路（ANN）以提高預測精度，然而進行預測以驗證從田口法和類神經網路模型中獲得其優化結果，結果表明透過ANN能準確預測輪盤的磨損，能將最佳關鍵的預測結果組合導入至智慧機械當中，使產業達到智慧工廠之理念目標。

Many studies show that the advancement and innovation of technologies can efficiently boost productivity in the manufacturing industry. As the industry faces crises such as lack of professional technical workforces and increasingly complex manufacturing processes, it accelerates the digital transformation in the manufacturing industry to solve the present problems. This study aims to enhance the performance of predicting the life cycle of abrasive discs in a weld run grinding machine. Taguchi method is employed to identify the possible combination of factors that cause the wear of abrasive discs by metal matrix composite to reduce the number of experiments. The objective function is aimed at smaller-the-better. In contrast, the Artificial neural network （ANN） algorithm predicts abrasive discs’ life cycle to improve the predicting accuracy. An empirical study validates the performance of ANN in predicting the wear of abrasive discs. The results show that grinding materials, feed rate, rotational speed, and applied force are highly correlated. The optimized abrasive parameters are obtained through the Design of Experiments （DOE） with Taguchi’s L9 orthogonal array. Besides that, the ANN model shows to predicts the abrasive discs’ life cycle accurately. This study is expected to shed light on the direction of intelligent manufacturing. In future research, some underlying uncertainties can be considered to overcome the limitation of this study .

摘要 ...i
Abstract ...ii
誌謝 ...iv
目錄 ...v
表目錄 ...viii
圖目錄 ...ix
第 一 章 緒論 ...1
1.1 研究背景 ...1
1.2 研究動機 ...2
1.3 研究目的 ...4
1.4 研究流程 ...5
第 二 章 文獻探討 ...7
2.1 金屬加工研磨種類 ...7
2.2 研磨架構層 ...7
2.3 表面粗糙度定義 ...8
2.4 表面加工受力值所影響產品的品質 ...9
2.5 六標準差定義 ...9
2.5.1 六標準差改善步驟 ...10
2.6 品質工程 ...10
2.7 品質特性 ...11
2.8 田口方法 ...11
2.8.1 品質損失函數 ...12
2.8.2 影響因子/信號比 ...12
2.9 直交表 ...13
2.10 類神經網路 ...15
2.10.1 類神經網路簡介 ...15
2.10.2 類神經網路應用 ...16
2.11 文獻總結 ...17
第 三 章 研究方法 ...18
3.1 研究架構 ...18
3.1.1 研究架構流程 ...19
第 四 章 金屬研磨加工改善範例 ...21
4.1 資料分析 ...21
4.2 分析階段 ...22
4.3 研究限制 ...22
4.4 控制因子 ...23
4.4.1 研磨耗材 ...23
4.4.2 焊道工件材 ...24
4.4.3 進給速率 ...25
4.4.4 BUFF施力 ...25
4.4.5 砂輪轉速 ...26
4.4.6 工具與平面焊道夾角 ...27
4.5 決定研磨加工關鍵因素 ...28
4.6 Minitab實驗設計 ...29
4.6.1 S/N比因子反應 ...30
4.6.2 品質特性的反應圖及反應表 ...31
4.6.3 製程最佳化 ...32
4.6.4 確認實驗 ...33
4.7 類神經網路之建構 ...34
4.7.1 資料預處理 ...34
4.7.2 資料分配 ...34
4.7.3 交叉驗證 ...35
4.7.4 收斂測試 ...36
第 五 章 結論與未來研究 ...37
5.1 結論 ...37
5.2 未來研究方向 ...37
參考文獻 ...38
Extended Abstract ...43

1.田欣利、王龍、郭昉、王望龍、雷蕾(2016)。《小砂輪軸向大切深緩進給磨削的磨損特徵》https://kknews.cc/zh-tw/news/leyar9.html
2.林豐澤（2005）。演化式計算上篇：演化式演算法的三種理論模式。智慧科技與應用統計學報，3（1），1。
3.黃漢邦（1991）。如何做到智慧型控制？──神經網路在控制上的應用。科學月刊，第二十二卷，第259期，第495-503頁。
4.廖家宜（2022）。高鋼價時代 手工具、扣件業等下游業者如何延續外銷佳績？https://www.digitimes.com.tw/iot/article.asp?cat=158&cat1=20&cat2=&id=627821
5.Al-Hazza, M. H. F., bt Ibrahim, N. A., Adesta, E. T., Khan, A. A., & Sidek, A. B. A. （2017, March）. Surface roughness optimization using Taguchi Method of high speed end milling for hardened steel D2. In IOP Conference Series： Materials Science and Engineering （Vol. 184, No. 1, p. 012047）. IOP Publishing.
6.Asiltürk, I., & Çunkaş, M. （2011）. Modeling and prediction of surface roughness in turning operations using artificial neural network and multiple regression method. Expert systems with applications, 38（5）, 5826-5832.
7.Bisgaard, S. （1990）. Quality engineering and Taguchi methods： a perspective.
8.Brezocnik, M., & Kovacic, M. （2003）. Integrated genetic programming and genetic algorithm approach to predict surface roughness. Materials and manufacturing processes, 18（3）, 475-491
9.Chen, J. C., Li, Y., & Cox, R. A. （2009）. Taguchi-based Six Sigma approach to optimize plasma cutting process： an industrial case study. The International Journal of Advanced Manufacturing Technology, 41（7-8）, 760-769.
10.Di Benedetto, R. M., Botelho, E. C., Janotti, A., Junior, A. A., & Gomes, G. F. （2021）. Development of an artificial neural network for predicting energy absorption capability of thermoplastic commingled composites. Composite Structures, 257, 113131.
11.Heyn, J., Gümbel, P., Bobka, P., Dietrich, F., & Dröder, K. （2019）. Application of artificial neural networks in force-controlled automated assembly of complex shaped deformable components. Procedia CIRP, 79, 131-136.
12.Ikumapayi, O. M., & Akinlabi, E. T. （2019）. Experimental data on surface roughness and force feedback analysis in friction stir processed AA7075–T651 aluminium metal composites. Data in brief, 23, 103710.
13.International journal of machine tools and manufacture, 45（4-5）, 467-479.
14.Kadam, B. J., & Mahajan, K. A. （2021）. Optimization of cutting temperature in machining of titanium alloy using Response Surface Method, Genetic Algorithm and Taguchi method. Materials Today： Proceedings.
15.Kaladgi, A. R., Afzal, A., Manokar, A. M., Thakur, D., Agbulut, U., Alshahrani, S., & Subbiah, R. （2021）. Integrated Taguchi-GRA-RSM optimization and ANN modelling of thermal performance of zinc oxide nanofluids in an automobile radiator. Case Studies in Thermal Engineering, 26, 101068.
16.Khare, S. K., Agarwal, S., & Srivastava, S. （2018）. Analysis of surface roughness during turning operation by Taguchi method. Materials Today： Proceedings, 5（14）, 28089-28097.
17.Ko, D. C., Kim, D. H., & Kim, B. M. （1999）. Application of artificial neural network and Taguchi method to preform design in metal forming considering workability. International Journal of Machine Tools and Manufacture, 39（5）, 771-785.
18.Kumar, B. R., Vardhan, H., Govindaraj, M., & Vijay, G. S. （2013）. Regression analysis and ANN models to predict rock properties from sound levels produced during drilling. International Journal of Rock Mechanics and Mining Sciences, 58, 61-72.
19.Kumar, S. R., & Kulkarni, S. K. （2017）. Analysis of hard machining of titanium alloy by Taguchi method. Materials Today： Proceedings, 4（10）, 10729-10738.
20.Li, M. H. C., Al-Refaie, A., & Yang, C. Y. （2008）. DMAIC approach to improve the capability of SMT solder printing process. IEEE Transactions on Electronics Packaging Manufacturing, 31（2）, 126-133.
21.Li, Y., Li, Y. F., Wang, Q. L., Xu, D., & Tan, M. (2009). Measurement and defect detection of the weld bead based on online vision inspection. IEEE Transactions on Instrumentation and Measurement, 59(7), 1841-1849.
22.Mohan, N. S., Kulkarni, S. M., & Ramachandra, A. （2007）. Delamination analysis in drilling process of glass fiber reinforced plastic （GFRP） composite materials. Journal of Materials Processing Technology, 186（1-3）, 265-271.
23.Nisar, L., Banday, B., Amatullah, M., Farooq, M., Thoker, A. N., Maqbool, A., & Wahid, M. A. （2021）. An investigation on effect of process parameters on surface roughness and dimensional inaccuracy using Grey based Taguchi method. Materials Today： Proceedings.
24.Oktem, H., Erzurumlu, T., & Erzincanli, F. （2006）. Prediction of minimum surface roughness in end milling mold parts using neural network and genetic algorithm. Materials & design, 27（9）, 735-744.
25.Özel, T., & Karpat, Y. （2005）. Predictive modeling of surface roughness and tool wear in hard turning using regression and neural networks.
26.Ridwan, F., & Xu, X. （2013）. Advanced CNC system with in-process feed-rate optimisation. Robotics and Computer-Integrated Manufacturing, 29（3）, 12-20.
27.Taguchi, G. （1995）. Quality engineering （Taguchi methods） for the development of electronic circuit technology. IEEE Transactions on Reliability, 44（2）, 225-229.
28.Wang, Z., & Bovik, A. C. （2009）. Mean squared error： Love it or leave it? A new look at signal fidelity measures. IEEE signal processing magazine, 26（1）, 98-117.
29.Yang, W. H. P., & Tarng, Y. S. （1998）. Design optimization of cutting parameters for turning operations based on the Taguchi method. Journal of materials processing technology, 84（1-3）, 122-129.
30.Zhang, J. Z., Chen, J. C., & Kirby, E. D. （2007）. Surface roughness optimization in an end-milling operation using the Taguchi design method. Journal of materials processing technology, 184（1-3）, 233-239.