由於半導體產業市場需求以及封裝測試技術的不斷變化與進步，使得必須經常購買新世代昂貴的機台設備來應付產業趨勢，對於資本支出為極大的負擔，因此該如何有效利用現有機台設備以提升生產效率是相當重要的。目前半導體業有一個常用來衡量生產效率的指標稱為設備綜合效力(Overall Equipment Effectiveness, OEE)，能夠有效衡量設備的使用效率，而由於影響OEE的因子太過於錯綜複雜，業者通常以固定OEE值(70 %)來估算接單的標準成本。因此若能建構OEE預測模式，便能提高客戶報價之標準成本估算的準確度；另一方面找出提供OEE的改善方向，對於生產排程和顧客服務也能提供比較好的控制。
本研究方法分為三大部分：首先推導OEE成本模式，以說明OEE對於製造成本的重要影響，接下來試圖以因素分析找出影響OEE的背後共同影響以利尋找未來OEE的改善方向。最後建構半導體業的OEE預測模式，並比較不同預測模式：複迴歸分析、倒傳遞網路(back-propagation neural network, BPN)、複合式預測模式，並以某半導體測試廠收集資料比較其預測績效之差異。
經由推導及實証結果，在目前OEE之基準下，當OEE增加1 %後，所能減少的製造成本加上額外貢獻的收益佔預估總製造成本約2.74 %。經由因素分析，提出五項影響OEE的重要因素。最後建議以複合式預測模式來建構OEE預測模型，相較於目前業界以70 %之固定值去估算OEE來比較，MSE約有69.6 %的改善率，MAE則達48.8 %。

Abstract
How to fully utilize the equipment to improve the production efficiency is very important to the semiconductor industries. Besides it is a heavy burden for the industry to invest on newer equipment because of the constantly changed demand and the continuously advanced technology in the industry. Overall Equipment Effectiveness (OEE), a common metric to measure the production efficiency, has been adopted completely in the semiconductor industry for calculating the production efficiency. However, it is difficult for the companies to estimate the OEE correctly and they usually use a fixed OEE rate, 70 %, as the standard OEE. Therefore, this study aims to construct OEE estimation model and find the factors influencing OEE in order to find ways improving OEE. And this model will help to make the production schedule better and to have better customer service.
In this study, we first model the relationship between OEE and manufacturing cost to show the importance of OEE estimation. Then, the latent factors influencing OEE can be discovered by factor analysis. Finally we construct OEE estimation model by three methods: multiple regression analysis, back-propagation neural network, and compound estimation model. The verifification of model’s estimation performance via a case study of an IC testing house is performed.
Through empirical analysis, the ratio of the decreasing manufacturing cost and the increasing contribution profit to total manufacturing cost is about 2.74 % when OEE rate increases 1 % under the current OEE level. Furthermore, five latent factors are presented by factor analysis to provide the improving directions of OEE for managers. Finally, we show the estimated OEE model has significant improvement compared to the current OEE estimation.

中文部份
王忠誠，IC測試設備（分類機）開發評估-以成品系統層級測試自動化應用為例，國立清華大學工業工程與工程管理研究所碩士論文，2004年。
半導體工業年鑑，半導體工業年鑑，工業技術研究院電子工業研究所，2005年。
唐麗英，王春和，STATISTICA 6.0 版與基礎統計分析，儒林圖書有限公司，2003年。
陳順宇, 鄭碧娥，STATISTICA手冊(1)：基本統計，華泰書局，1999年。
陳順宇，迴歸分析（三版），華泰書局，2000年。
陳順宇，多變量分析（三版），華泰書局，2004年。
張智星，MATLAB程式設計與應用，清蔚科技，2000年。
彭昭英，SAS與統計分析，儒林圖書有限公司，2004年。
葉怡成，類神經網路模式應用與實作（八版），儒林圖書有限公司，2003年。
羅華強，類神經網路-MATLAB的應用，清蔚科技股份有限公司，2001年。

西文部份
Ali, L., Sidek, R., Aris, I., Suparjo, B. S., and Ali, M. A. M., Challenges and directions for testing IC. INTEGRATION, the VLSI journal, 37, 17-28, 2004.
Ames, V. A., Gililland, J., Konopka, J., Schnabl, R. and Barber, K., Semiconductor Manufacturing Productivity: Overall Equipment Effectiveness (OEE) Guidebook. International SEMATECH, Report Technology Transfer 95032745A-GEN, 1995.
Chand, G., and Shirvani, B., Implementation of TPM in cellular manufacture. Journal of Materials Processing Technology, 103, 149-154, 2000.
Chang, S. C., Lai, H. C., and Yu, H. C., A variable P value rolling Grey forecasting model for Taiwan semiconductor industry production. Technological Forecasting and Social Change, 72(5), 623-640, 2005.
Chiang, W. C., Urban, T. L., and Baldridge, G. W., A neural network approach to mutual fund net asset value forecasting. OMEGA International Journal of Management, Science, 24(2), 205-215, 1996.
Chu, C. W., and Zhang G. P., A comparative study of linear and nonlinear models for aggregate retail sales forecasting. International Journal of Production Economics, 86(3), 217-231, 2003.
Couvêa da Costa, S. E., and Prnheiro de Lima, E., Uses and misuses of the ‘overall equipment effectiveness’ for production management. In Proceeding of IEEESEMI Advanced International. Semiconductor Manufacturing Science Symposium, 816-820, 2002.
Dal, B., Tugwell, P., and Greatbanks, R., Overall equipment effectiveness as a measure of operational improvement-A practical analysis. International Journal of Operations & Production Management, 20(12), 1488-1502, 2000.
Dance, D. L., and Jimenez, D. W., Semiconductor equipment performance metrics: Cost of ownership and overall equipment effectiveness. Semiconductor International, 19(13), 6-8, 1996.
Dance, D. L., Jimenez, D. W., and Levine, A. L., Understanding equipment cost-of-ownership. Semiconductor International, 21(8), 117-118, 120, 122, 1998.

de Ron, A. J., and Rooda, J. E., Equipment effectiveness: OEE revisited. IEEE Transactions on Semiconductor Manufacturing, 18(1), 190-196, 2005.
Drezga, I., and Rahman, S., Input variable selection for ANN-based short-term load forecasting. IEEE Transactions on Power Systems, 13(4), 1238-1244, 1998.
Gaafar, L. K., and Choueiki, M. H., A neural network model for solving the lot-size problem. Omega, 28(2), 175-184, 2000.
Glorfeld, L. W., A methodology for simplification and interpretation of backpropagation-based neural network models. Expert System with applications, 10(1), 37-54, 1996.
Hagan, M. T., and Menhaj, M. B., Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6), 989-993, 1994.
Hipkin, I. B., and Cock, C. D., TQM and BPR: lessons for maintenance management. Omega, 28(3), 277-292, 2000.
Huang, S. H., Dismukes, J. P., Shi, J., Su, Q., Razzak, M. A., Bodhale, R., and Robinson, D. E., Manufacturing productivity improvement using effectiveness metrics and simulation analysis. International Journal of Production Research, 41(3), 513-527, 2003.
Jain, B. A., and Nag, B. N., Artificial neural network models for pricing initial public offerings. Decision Sciences, 26(3), 283-302, 1995.
Jonsson, P., and Lesshammar, M., Evaluation and improvement of manufacturing performance measurement systems-The role of OEE. International Journal of Operations & Production Management, 19(1), 55-78, 1999.
Karri, V., and Frost, F., Optimum back propagation network conditions with respect to computation time and output accuracy. Proceedings of Third International Conference on Computational Intelligence and Multimedia Applications (ICCIMA '99), 50-54, 1999.
Konopka, J. M., Capacity Utilization Bottleneck Efficiency System-CUBES. IEEE Transactions on Components, Packaging, and Manufacturing Technology-Part A, 18(3), 484-491, 1995.

Kwon, O., and Lee, H., Calculation methodology for contributive managerial effect by OEE as a result of TPM activities. Journal of Quality in Maintenance Engineering, 10(4), 263-272, 2004.
Leachman, R. C., Closed-loop measurement of equipment efficiency and equipment capacity. IEEE Transactions on Semiconductor Manufacturing, 10(1), 84-97, 1997.
Lee, K., Booth, D., and Alam, P., A comparison of supervised and unsupervised neural networks in predicting bankruptcy of Korean firms. Expert Systems with Applications, 29, 1-16, 2005.
Lee, T. L., Back-propagation neural network for long-term tidal predictions. Ocean Engineering, 31, 225-238, 2004.
Oechsner, R., Pfeffer, M., Pfitzner, L., Binderb, H., Müller, E., and Vonderstrass T., From overall equipment efficiency (OEE) to overall Fab effectiveness (OFE). Materials Science in Semiconductor Processing, 5, 333-339, 2003.
Paraszczak, J., Understanding and assessment of mining equipment effectiveness. Mining Technology: Transactions of the Institute of Mining & Metallurgy, Section A, 114(3), 147-151, 2005.
SEMATECH, Standard for Definition and Measurement of Equipment Reliability, Availability, and Maintainability (RAM). International SEMATECH, Report SEMI E10-0699, 1999.
SEMATECH, Standard for Definition and Measurement of Equipment Productivity. International SEMATECH, Report SEMI E79-0200, 2000.
Tafeit, E., Möller, R., Sudi, K., and Reibnegger, G., Artificial neural networks compared to factor analysis for low-dimensional classification of high-dimensional body fat topography data of healthy and diabetic subjects. Computers and Biomedical Research, 33, 365-374, 2000.
Vellidoa, A., Lisboa, P. J. G., and Vaughan, J., Neural networks in business: a survey of applications (1992–1998). Expert Systems with Applications, 17, 51-70, 1999.
Walczak, S., Categorizing university student applicants with neural networks. Proceeding of IEEE International Conference on Neural Networks, 6, 3680-3685, 1994.

Walczak, S., and Cerpa, N., Heuristic principles for the design of artificial neural networks. Information and Software Technology, 15, 107-117, 1999.
Walczak, S., An empirical analysis of data requirements for financial forecasting with neural networks. Journal of Management Information Systems, 17(4), 203-222, 2001.
West, P. M., Brockett, P. L., and Golden, L. L., A comparative analysis of neural networks and statistical methods for predicting consumer choice. Marketing Science, 16(4), 370-391, 1997.
White, G. P., A survey and taxonomy of strategy-related performance measures for manufacturing. International Journal of Operations & Production Management, 16(3), 42-51, 1996.
Wong, B. K., Bodnovich, T. A., and Selvi, Y., Neural network applications in business: A review and analysis of the literature (1988-95). Decision Support Systems, 19(4), 301-320, 1997.