在面板產業中，光學膠對客戶貼合製程的品質穩定性直接影響平板顯示器的光學性能與市場競爭力，但常因產品不穩定與缺陷率偏高而導致生產損失。由於傳統經驗導向的改善方式缺乏完整製造流程分析支撐，難以持續優化並建立穩健性系統，極需運用系統化方法識別關鍵參數並建立製程最佳化操作條件。
　　文獻中已有諸多關於製程參數最佳化之實驗設計法應用，本研究為確保能通盤考量完整製程中的所有因子，不再只限縮於機台參數，故結合六標準差當中的DMAIC流程與田口實驗設計，搭配最佳化實驗設計與反應曲面法之最陡上升坡度，以期能在最短的時間內識別關鍵因子，並使用較少的實驗次數獲得有效的參數最佳解。本研究於DMAIC流程中確立關鍵品質特性，並逐步篩選出關鍵要因；於田口實驗設計採用L_16 (2^15 )正交表進行實驗設計，計算信噪比並以變異數分析量化各因子效應，搭配ANOVA分析，快速識別影響良率之因子，進而運用響應曲面法沿最陡升路徑尋求最佳操作條件，最後DMAIC中之管控流程，制定過程監控機制以維持改善成果。驗證結果顯示，改善後平均良率達98.8%，較初始良率89%提升9%，且根據製程能力指數與製程績效指標顯示製程具有良好穩定性。
　　DMAIC五大流程與實驗設計之整合框架，相較於經驗法則，該方法能精確識別關鍵因子並實現有效率的顯著改善，確保了統計實驗設計在個案公司新產品製程品質提升中的有效性，並提供了可複製的應用模式。

This study investigates yield instability during new product introduction in Optically Clear Adhesive (OCA) film manufacturing, where traditional experience-based approaches lack systematic parameter analysis. The objective is to integrate DMAIC, a Six Sigma methodology, with experimental design for comprehensive process optimization. Process map identifies input variables, while Cause-and-Effect Matrix and FMEA screen critical factors. The Improve phase implements three-stage experimental optimization: Taguchi method employs orthogonal arrays for initial parameter screening with 48 runs, I-Optimality design evaluates factor interactions, and response surface methodology applies steepest ascent for parameter fine-tuning. SPC mechanisms established in the Control phase ensure sustained improvements. Implementation achieves 98.8% yield, exceeding 95% customer requirements. Process capability analysis reveals Cpk=1.96 and Ppk=2.01, both surpassing 1.67, confirming Six Sigma performance standards. The systematic approach requires only 110 experimental runs versus thousands for full factorial designs. The integrated DMAIC and DOE framework successfully replaces experience-based adjustments with data-driven optimization, providing a replicable model for future new product introductions while significantly reducing trial costs and stabilization time.

6Sigma.us. (2024). Cause and effect matrix: Complete guide with examples and tips. Retrieved August 17, 2025, from https://www.6sigma.us/cause-and-effect-matrix/cause-and-effect-matrix-complete-guide-with-examples-and-tips/
Abrahamson, J. T., Beagi, H. Z., Salmon, F., & Campbell, C. J. (2019). Optically clear adhesives for OLED. In S. Pyshkin (Ed.), Luminescence - OLED technology and applications. London, UK: IntechOpen
Antony, J. (2014). Design of experiments for engineers and scientists (2nd ed.). Amsterdam, Netherlands: Elsevier.
Becerra, M., & Goos, P. (2021). Bayesian I-optimal designs for choice experiments with mixtures. Chemometrics and Intelligent Laboratory Systems, 217, Article 104395.
Box, G. E. P., & Wilson, K. B. (1951). On the experimental attainment of optimum conditions. Journal of the Royal Statistical Society: Series B (Methodological), 13(1), 1–38.
Costa, J. P., Lopes, I. S., & Brito, J. P. (2019). Six Sigma application for quality improvement of the pin insertion process. Procedia Manufacturing, 38, 1592-1599. Amsterdam, Netherlands: Elsevier.
Filz, M.-A., Langner, J. E. B., Herrmann, C., & Thiede, S. (2021). Data-driven failure mode and effect analysis (FMEA) to enhance maintenance planning. Computers in Industry, 129, Article 103451.
Goos, P., & Jones, B. (2011). Optimal design of experiments: A case study approach. Hoboken, NJ: Wiley.
Hii, D. H., Muhammad, N. A., & Muhammad, N. (2024). Synergizing FMEA and PDCA for superior risk management and process improvement in the semiconductor industry: A case study. International Journal of Production Management and Engineering, 12(2), 180–194.
Huang, Y., Gilmour, S. G., Mylona, K., & Goos, P. (2019). Optimal design of experiments for non-linear response surface models. Journal of the Royal Statistical Society: Series C (Applied Statistics), 68(3), 623-640.
International Organization for Standardization. (2014). ISO 22514-1:2014: Statistical methods in process management—Capability and performance—Part 1: General principles and concepts. https://www.iso.org/standard/64135.html
Jones, B., Allen-Moyer, K., & Goos, P. (2020). A-optimal versus D-optimal design of screening experiments. Journal of Quality Technology, 53(4), 369–382.
Leu, Y., & Lin, C.-M. (2021). Optimizing optical film lamination to enhance the luminance of TFT-LCD displays using the Taguchi-NNGA method. Materials, 14(16), 4481.
Minitab, LLC. (2021). Minitab Statistical Software (Version 20.2) [Computer software]. State College, PA: Minitab, LLC.
Monday, L. M. (2022). Define, Measure, Analyze, Improve, Control (DMAIC) methodology as a roadmap in quality improvement. Global Journal of Quality & Safety in Healthcare, 5(2), 44–46.
Montgomery, D. C. (2020). Design and analysis of experiments (10th ed.). Hoboken, NJ: Wiley.
Myers, R. H., Montgomery, D. C., & Anderson-Cook, C. M. (2016). Response surface methodology: Process and product optimization using designed experiments (4th ed.). Hoboken, NJ: Wiley.
OCA for Film Type Touch Sensor. (2025, August). Opteria products. Retrieved August 14, 2025, from https://www.opteria-global.com/en/products/mo/sensor.html
Park, Y., Kim, J., Kim, D., Lee, S., Hwang, D., & Kwon, M. S. (2024). Towards the optimal design of optically clear adhesives for flexible display. Soft Science, 4(3), Article 28.
Peruchi, R. S., Paiva, A. P., Balestrassi, P. P., Ferreira, J. R., & Sawhney, R. (2014). Weighted approach for multivariate analysis of variance in measurement system analysis. Precision Engineering, 38(3), 651-658.
Peruchi, R. S., Rotela Junior, P., Brito, T. G., Paiva, A. P., Balestrassi, P. P., & Mendes Araujo, L. M. (2020). Integrating multivariate statistical analysis into Six Sigma DMAIC projects: A case study on AISI 52100 hardened steel turning. IEEE Access, 8, 34246-34255.
Phadke, M. S. (1989). Quality engineering using robust design. Englewood Cliffs, NJ: Prentice Hall.
Quality-One. (2025). Measurement systems analysis (MSA). Retrieved August 11, 2025, from https://quality-one.com/msa/
Ross, P. J. (1996). Taguchi techniques for quality engineering (2nd ed.). New York, NY: McGraw-Hill.
Roy, R. K. (2010). A primer on the Taguchi method (2nd ed.). Dearborn, MI: Society of Manufacturing Engineers.
Stallrich, J. W., Allen-Moyer, K., & Jones, B. (2023). D- and A-optimal screening designs. Technometrics, 65(4), 492–501.
Stat-Ease, Inc. (2021). Design-Expert (Version 13) [Computer software]. Minneapolis, MN: Stat-Ease, Inc.
Singh, M., & Xie, W. (2020). Approximation algorithms for D-optimal design. Mathematics of Operations Research, 45(4), 1193-1620.
Taguchi, G. (1986). Introduction to quality engineering: Designing quality into products and processes. Tokyo, Japan: Asian Productivity Organization.
Touch Screen Display Market. (2025, February). Global Touch Screen Display Market By Type (Capacitive Touch Screens, Resistive Touch Screens, Optical and Others), By Application, By End User - Global Industry Outlook, Key Companies (BOE Technology Group Co Ltd, AU Optronics Corp, Innolux Corp and others), Trends and Forecast 2023-2032. Retrieved August 11, 2025, from https://dimensionmarketresearch.com/report/touch-screen-display-market/#overview/