由於TFT-LCD產品價格不斷下降，各企業無不想盡各種方法降低生產與庫存成本，其中零組件偏光板製造業是屬於高材料成本的產業，因此，如何降低原物料投入成本是非常重要的工作。目前偏光板製造廠在生產數量規劃，依然採用一般固定良率的方式，由於各製程之良率變動會影響到整個生產數量規劃的合理性，因此，須將良率的變化納入考量，才能反應出實際的生產狀況與生產成本，並期望在有考量學習效應的情況下，藉由小尺寸過去的生產經驗，預測未來大尺寸之良率變化，使公司資源做更完善的安排與利用，進而降低原物料投入成本與庫存成本。
　　隨著TFT-LCD技術與對比的提升，大尺寸顯示器需求也隨之成長，然而大尺寸材料成本相對較高，若在生產規劃中未能考慮良率變化，而投入過多的原物料，很容易造成材料與庫存成本的增加，因此更加顯示出構建生產學習模式之重要性。因此，本研究使用過去一年的生產資料，透過非線性支援向量迴歸方法，建構小尺寸及大尺寸之生產模式，並藉由單個抽出交叉確認法(Leave-one-out Cross-Validation)驗證預測結果是否在可接受範圍內，期望在有考量學習效應的情況下，能減少許多不必要的投入量，以降低原物料成本支出。藉由研究與分析所發展出來的良率預測模式，可提供偏光板製造商未來在生產大尺寸產品時可參考的工具。
　　因此，本研究透過驗證提出四種不同的生產模式，依據不同的生產情況與背景，建議分別適用於不同的生產模式，使企業更能掌控生產良率的變化，以有效達到降低生產成本的目標。

　　Due to the TFT-LCD product price drops continuously, many companies think any ways to reduce the production and the stock cost all. One of the Components Polarizer of manufacturing industry is belong to industry of high material cost, it is very important that how to reduce raw material input-cost. At present, Polarizer manufactory still use the way of ordinary-firm-yield in the production quantity plan. Because various systems of the yield change can affect the entire production quantity plan rationality. Therefore, we must integrate the yield with the consideration. It can respond the actual production condition and the production cost, and it is expected that in the consideration study effect situation, by the past production experience of the small-size, forecast change to the future that great-size of yield. Causes the company resources to make the more perfect arrangement and exploitation, and then reduces the original material investment-cost and the stock-cost.
　　Along with TFT-LCD technology and contrast promotion, great-size monitor demand also growth, however, great-size material cost relative high. If you has not been able to consider the yield change in the production plan, but invests excessively many original materials, which very easy to create the material and the stock cost increase. Therefore, it even more demonstrates importance of the construction production study mode. For this reason, this research use production information for the past year, and permeate the way of Support Vector Regression (SVR), which constructs production mode of the small-size and the great-size. By the way of Leave-one-out Cross-Validation to confirm the forecast result whether it can be accepted in the scope or not. Expected in the study effect situation, it can reduce so many nonessential inputs that decrease disbursement of the original material cost. It develops that the yield forecast mode through research and analysis, In the future, the tool which might provide referral about the polarizer manufacturer when to produce great-size product.
　　For this reason, this research through confirmation proposed four kind of different production modes. According to the different production situation and the background, and suggested that apply separately to different production mode. It enables the industry control to produce yield change, and achieved the goal which reduces effectively the production cost.

【中文部份】
呂中元，陳文哲，「製衣業車縫作業學習曲線之研究」，國立交通大學管理科學研究所碩士論文，1981年。
池耀宇，「實證探討台灣高科技產業投資行為與資本結構-線性迴歸模式與類神經網路模式」，國立交通大學管理科學研究所未出版碩士論文，2001年。
李希豪，袁建中，「學習曲線在飛機工業應用之研究 — 以我國航空業飛機結構組裝為例」，國立交通大學科技管理研究所碩士論文，1992年。
苗延仁，汪守仁「學習曲線在少量製造成本上的應用」，國立台灣科技大學工程技術研究所工業管理組碩士論文，1986年。
張春興，楊國樞，「心理學」，第一版，三民書局，1973年。
許智欽，「國內育成中心績效模式之建構與驗證-以多元迴歸分析法」，實踐大學企業管理研究所未出版碩士論文，2004年。
陳冠羽，楊金福，「IC製造業應用學習曲線於成本模式之研究」，國立交通大學工業工程與管理研究所碩士論文，1998年。
韓歆儀，「應用兩階段分類法提昇SVM法之分類準確率」，國立成功大學工業與資訊管理研究所碩士論文，2004年。
【英文部份】
Alchian, T.K., “Reliability of progress curves in airframe production,” Econometrica, vol.31, no.4, pp.679-693, 1963.
Alder, G.L. and Nanda, R., “The effects of learning on optimal lot size determination single product case,” IIE Transactions, vol.6, no.1, pp.14-20, 1974.
Arrow, K.J., “The economic implications of learning by doing,” Review of Economic Studies, vol.29, pp.166-170, 1962.
Baloff, N., “Extension of the learning curve：some empirical results,” Operations Research Quarterly, vol.22, vo.4, pp.329-340, 1971.
Bailey, C.D., “Forgetting and the learning curve：a laboratory study,” Management Science, vol.35, no.3, pp.340-352, 1989.
Bevis, F.W. and Towill, D.R., “Managerial control systems based on learning curve models,” International Journal of Production Research, vol., no.3, pp.219-238, 1972.
Camm, J.D., Gulledge, T.R., and Womer, N.K., “Production rate and contractor behavior,” Journal Cost Analysis, vol.5, no.1, pp.27-38, 1987.
Carlson, J.G., “Cubic learning curves：Pecision tool for labor estimating,” Manufacturing Engineering and Management, vol.71, no.5, pp.22-25, 1973.
Cherrington, J.E., Lippert, S., and Towill, D.R., “The effect of prior experience on learning curve parameters,” International Journal of Production Research, vol.25, no.3, pp.399-411, 1987.
Conway, R.W. and Schultz, J.R., “The manufacturing progress function,” Journal of Industry Engineering, vol.6, no.1, pp.39-53, 1959.
DeJong, J.R., “The effects of increasing skill on cycle time and its consequences for time standards,” Ergonomics, pp.51-60, Nov. 1957.
Drucker, H., Burges, C. J. C., Kaufman, L., A. Smola and V. Vapnik., “Support vector regression machine,” Advances in Neural Information Processing Systems, vol.5, no.1, pp.39-45, 1997.
Garg, A. and Milliman, P., “The aircraft progress curve modified for design changes,” Journal of Industry Engineering, vol.12, no.1, pp.23-27, 1961.
Globerson, S. and Shtub, A., “The impact of learning curves on the desing on long cycle time lines,” Industrial Management, vol.26, no.3, pp.5-10, 1984.
Glover, J.H., “An alternative model and its comparison with existing functions,” International Journal of Production Research, vol.4, no.4, pp.279-300, 1966.
Goldberger, A.S., “The interpretation and estimation of Cobb-Douglas functions,” Econometrica, vol.35, no.3, pp.464-472, 1968.
Greenberg, L., “Measurement of the work-accident experience in the American petroleum industry,” American Society Satety Engineers, vol.15, no.2, pp.11-13, 1970.
Gulledge, T.R., Womer, N.K., and Tarimcilar, M.M., “A discrete dynamic optimization model for made-toorder cost analysis,” Decision Sciences, vol.16, pp.73-90, 1985.
Hancock, W.M., “The prediction of learning rate for manual operations” Journal of Industry Engineering, vol.18, no.1, pp.42-47, 1967.
Hirschmann, W.B., “Profit from the learning curve,”Harvard Business Review, pp.105-119, Jan. 1964.
Hitchings, B. and Towill, D.R., “Error analysis of the time constant learning curves model,” International Journal of Production Research, vol.13, pp.105-135, 1975.
Howell, S.D., “Learning curves for new products,” Industrial Marketing Management, vol.9, no.2, pp.97-99, 1980.
Jean, P.S., “The uses and abuses of experience curves,” Long Rang Planning, vol.18, no.1, pp.65, 1985.
Knecht, G.R., “Costing, technological growth and generalized learning curves,” Operations Research Quarterly, vol.25, no.3, pp.487-491, Septtember, 1974.
Levy, F.K., “Adaptation in the production process,” Management, vol.4, no.1, pp.136-154, April, 1965.
McGehee, W. and Thayer, P.W., Training in Business and Industry, New York：John Wiley, pp.132, 1961.
McIntyre, E.V., “Cost-volume-profit analysis adjusted for learning,” Management Science, vol.10, no.5, pp.149-160, 1977.
Niganad, Y.J. and Bonney, M., “A comparative study of learning curves with forgetting,” Application Mathematics Modelling, vol.21, Auguest, 1997.
Pankaj, G., “Building strategy on the experience curve,” Harvard Business Review, pp.145-146, April, 1985.
Pegels, C.C., “On startup or learning curves：an expanded view,” AIIE Transactions, vol.1, no.3, pp.216-222, September, 1969.
Scholkopf, B. “Statistical Learning and Kernel Methods” Technical Report,Microsoft Research, Cambridge, 2000.
Sheshinski, E., “Test of the learning by doing hypothesis,” Review Economic and Statistics, vol.49, pp.568-578, 1967.
Tanner, J.P., “The learning curve,” Production Engineering, vol.32, no.5, pp.72-79, 1985.
Tommie, F.F., “Aircraft cost curves,” Deviation Analysis Projection Re-issued, August, 1963.Vapnik, V. N. “The Nature of Statistical Learning Theory” New York: Springer-Verlag, 1995.
Waller, E.W. and Dwyer, T.J., “Alternative techniques for use in parametric cost analysis,” Concepts Journal of Defense Systems Acquisition Management, vol.4, no.2, pp.48-59, 1981.
Womer, N.K., “Learning curves, production rate, and program costs,” Management Science, vol.25, no.4, pp.312-319, 1979.
Wright, T.P., “Factors affecting the cost of airplanes,” Journal of Aeronautical Sciences, vol.3, no.4, pp.122-128, February,1936.
Yelle, L.E., “Estimating learning curves for potential products,” Industrial Marketing Management, vol.5, pp.147-154, June, 1976.