隨著經營環境的全球化與激烈的競爭，企業必須做出迅速且適當的決策，以提升競爭力。目前半導體設備產業業務人員在制訂決策所需資訊的取得，往往須透過助理或工程人員整理，造成資訊在時效性上有所延誤。同時半導體設備為半導體產業重要的生產財，產業關聯性大，具有強調行銷服務之特性。因此，本研究的目的為提出一半導體設備產業訂單成本預測的方式，以協助業務人員可以快速的預測訂單成本以作出最有利的報價。一般而言，成本估算是半導體設備中重要的工作之一，其所估算出的訂單成本約可影響一個產品報價90%。因此正確、快速，精準的訂單成本估算報價、不僅影響公司的接單也影響公司獲利的高低。一般成本估算的方式皆為料(直接材料成本)、工(直接人工成本)、費(製造費用)的加總。但是往往業務人員對於新產品的材料不易估算、生產工時的計算與工作站生產流程不清楚、營運費用不知如何分配。導致報價的工作都落於工程或生產單位。但是工程單位及生產單位又對於業務人員訂單成本估算方式不甚清楚。進而影響訂單成本的正確性、時效性及精準性。因此利用類神經網路及線性迴歸發展一套訂單成本估算的模型對於業務人員是有必要性的。本研究希望藉此半導體設備訂單成本估算的模型可以改善業務人員現行的訂單成本估算的方式及時效性和精確性。

In today’s world, because the business environment has become more globalize and the competition has become more dramatic, corporations must make business decisions rapidly and accurately in order to stay competitive. Presently, the salesperson in the semiconductor equipment industry normally relies on assistants' or engineers' data collections before he or she can formulate strategic decisions, but sometimes the data process time can be very time consuming. As a result, it often delays the information delivery. For the meantime, semiconductor equipment is the mainstream of the production assets within the semiconductor industry and is highly related to production line and sales profitability. Due to that reason, the purpose of this thesis is to present a method to help project the cost of manufacturing semiconductor equipment so the salesperson can quickly provide a competitive and profitable quotation to his or her customers. Generally speaking, cost prediction is one of the most important processes within a semiconductor equipment manufacturer, and the calculated cost prediction can affect up to 90% of the equipment list price. A fast and accurate cost prediction not only gives companies the ability to receive higher order volumes but also increases companies' profitability. In most cases, the way to calculate cost of a product is to total the direct materials, direct labors, and manufacturing overheads. However, when a company introduces a new product, because salesperson is not familiar with the material cost, production time, production process, and shipping cost, he or she often relies on engineering or production department to come up with projected equipment quotation. On the flip side, engineering and production department may not fully understand salesperson’s cost prediction and analysis process. For this reason, the predicted cost may not be as accurately and correctly as it should be presented. It is determined that using artificial neural network and regression analysis to come up with a cost prediction model for salesperson is essential. Using the semiconductor equipment cost prediction model, the goal of this thesis is to help improve current salesperson’s cost prediction method and hence increase its accuracy and time efficiency.

中文部份
工研院經資中心，「國內半導體設備發展與市場切入之機會研究」，2006。
工研院機械所，「半導體製程設備技術發展四年計畫研究成果報告」，2006。
帆宣系統科技股份有限公司，「95年度半年報及股通會相關資料」，台灣證券交易所，股市公開資訊觀測站，2006。
吳柏林，「時間數列分析導論」，華泰文化，1995。
林真真、鄒幼涵，「迴歸分析」，華泰書局，1993。
陳順宇，「迴歸分析」，第三版，華泰書局，2004。
沛鑫半導體工業股份有限公司，「95年度半年報及股通會相關資料」，台灣證券交易所，股市公開資訊觀測站，2006。
哈建宇，「半導體設備產業現況及推動策略研究分析」，工研院產業經濟與資訊服務中心，2003。
葉怡成，「類神經網路模式應用與實作」，第七版，儒林圖書有限公司，2003。
游啟聰，「我國半導體產業國際競爭力分析」，經濟部，1999。
蘇哲民，TWVD2001一等水準觀測資料之系統誤差分析，成功大學測量工程研究所碩士論文，2003。

英文部份
Alon, I., M. Qi, R. J. Sadowski, “Forecasting aggregate retail sales: a comparison of artificial neural networks and traditional methods,” Journal of Retailing and Consumer Services, 2001.
Berry, M. J. A., and Linoff, G. S. “Data Mining Techniques: for marketing, sales,andcustomer support,” John Wiley & Sons, New York, 1997.
Bode, J., “Decision support with neural networks in the management of research and development:concepts and application to cost estimation,” Information &Management, 1998.
Bode, J., “Neural networks for cost estimation: simulations and pilot application,” International Journal of Production Research, 2000.
Bode, J., S. Ren, Z. Shi, “Application of 3-layer perceptrons to cost estimation,” IEEE International Conference on Neural Networks, 1995.
Chu, C.W., G.P. Zhang, “A comparative study of linear and nonlinear models for aggregate retail sales forecasting,” International Journal of Production Economics, 2003.
Davis, J., and Brozovsky, J. A., “Decision support software for tax,” The Tax Adviser, 1995.
Hagan, M. T., M.B. Menhaj. “Training feedforward networks with the Marquardt algorithm,” IEEE Transactions on Neural Networks, 1994.
Han, K., and Kamber, M., “Data Mining:Concepts and Techniques,” Morgan Kaufmann, CA, 2001.
Hsu, C. H., B. C. Jiang, E. S. Lee, “Fuzzy neural network modeling for product development,” Mathematical and Computer Modeling, 1999.
Lee, A., C. H. Cheng, J. Balakrishnan, “Software development cost estimation: integrating neural network with cluster analysis,” Information & Management, 1998.
Kumar, “Compariosn of neural networks and regression analysis: A new insight,” Expert Systems with Applications, 2005.
Kuo, R. J., K. C. Xue, “A decision support system for sales forecasting through fuzzy neural networks with asymmetric fuzzy weights,” Decision Support Systems, 1998.
López, G., M. A. Rubio, M. Martínez, F. J. Batlles, “Estimation of hourly global photo synthetically active radiation using artificial neural network models,” Agricultural and Forest Meteorology, 2001.
Lotfi, A., M. Howarth, “Industrial application of fuzzy systems: adaptive fuzzy control of solder paste stencil printing,” Journal of Information Sciences, 1998.
Luxhój, J. T., J. O. Riis, B. Stensballe, “A hybrid econometric-neural network modeling approach for sales forecasting,” International Journal of Production Economics, 1996.
Montgomery C.,Runger C.&Hubele F., Engineering Statistics, John Wiley & Sons, Inc., 2004.
Pham, D. T., E. Oztemel, “Control chart pattern recognition using learning vector quantization networks,” International Journal of Production Research,1994.
Samaon, B., D. Ellison, P. Dugard, “Software cost estimation using an Albus perceptron（CMAC）,” Information and Software Technology, 1997.
Sanzogni, L., D. Kerr, “Milk production estimates using feed forward artificial neural networks,” Computers and Electronics in Agriculture, 2001.
Shtub, A., R. Versano, “Estimating the cost of stell pipe bending, a comparison between neural networks and regression analysis,” International Journal of Production Economics, 1999.
Venugopal, V., and Baets, W., “Neural Networks and Statistical Techniques in Marketing Research: A Concept Comparison,” Marketing Intelligence & Planning, 1994,
Vellidoa, A., P.J.G. Lisboa, J. Vaughan, “Neural networks in business:a survey of applications,” Expert Systems with Application,1999.
Woo, H. G., H. S. Cho, “Estimation of hardened layer dimensions in laser surface hardening processes with variations of coating thickness,” Surface and Coating Technology, 1998.
Yea, B., T. Osaki, K. Sugahara, R. Konishi, “Improvement of concentration-estimation algorithm for inflammable gases utilizing fuzzy rule-based neural networks,” Sensors and Actuators B: Chemical, 1999.
Zhang, Y. F., J. Y. H. Fuh, “A neural network approach for early cost estimation of packaging products,” Computers and Industrial Engineering, 1998.
Zhang, Y.F., J.Y.H.Fuh, W.T.Chan “Feature-based cost estimation for packaging products using neural networks,” Computers in Industry, 1996.
Zhou, M., J. E. D. Gauthier, “A new method for adiabatic flame temperature estimations of hydrocarbon fuels,” Fuel, 1999.

相關網址
工研院經資中心，http://www.itis.org.tw/
電子工程專輯，http://www.eettaiwan.com/