良率直接且大幅影響生產之成本，製造者希望可在產品研發與量產階段快速提升良率。換言之，當良率發生問題，影響良率之根本原因需快速被找出。為達成此目標，傳統良率管理系統蒐集各式與生產相關之資訊，進行巨量數據分析期能找出良率問題之根本原因並給予修復改善。然而，隨著產業規模越來越大與製程複雜度提高，無論是面板、半導體或工具機產業，工廠內部之資料皆快速膨脹且愈漸複雜，致搜尋根本原因之過程變得極為困難，此生產情境隱含著高維度參數選擇之問題。
為解決此困境，本研究提出關鍵參數搜尋演算法架構，包含資料前處理、資料品質評估模組、演算法模組、信心指標模組與盲站搜尋模組。以生產路徑資料、製程資料、站點間量測、缺陷與最終量測做為輸入，輸出結果則為可能造成良率問題之關鍵機台或可能造成良率發生之關鍵製程參數，並有信賴指標與可能造成良率損失之盲站與以輔助。此架構最後以TFT-LCD實際資料進行案例呈現及驗證，證明KSA為有效搜尋影響良率根本原因之系統工具。

Product yield directly affects production cost. Thus, manufacturers seek to quickly enhance product yield during the development and mass-production processes. In other words, when a yield loss occurs, the root causes should be found rapidly in both the development and mass-production phases. When a yield loss is encountered, the traditional yield enhancement approach is to collect all production-related data to perform big data analysis in order to find out the root causes of affecting yield and remedy them. However, production-related data are extremely large and complicated in various industries such as TFT-LCD, semiconductor or tool machine, which makes it hard to search for the root causes of a yield loss. This leads to the problem of high-dimensional variable selection. To solve this problem, a scheme of Key-variable Search Algorithms (KSAs) is proposed in this paper. The KSA scheme includes data preprocessing, data quality check module, KSA module, reliance index module and blind-stage search module. The inputs of this KSA scheme include production routes, process data, inline data, defects, and final inspection results; while the outputs are search results and their corresponding reliance indices as well as blind stages. The search results are the key stages that cause the yield loss or the key variables that are the root causes of the yield loss. The thin film transistor-liquid crystal display (TFT-LCD) process is adopted as the illustrative example to demonstrate that the KSA scheme is a promising tool to find out the root cause of yield losses.

[1] L. Fowler and T. Davis, “Engineering data analysis using Discovery,” IEEE/SEMl Advanced Semiconductor Manufacturing Conference, pp 416 - 422, November 1996.
[2] H. Cheng, M. P. L. Ooi, Y. C. Kuang, E. Sim, B. Cheah, S. Demidenko, “Automatic Yield Management System for Semiconductor Production Test”, 2011 Sixth IEEE International Symposium on Electronic Design, Test and Application (DELTA), pp. 254-258, 2011.
[3] F. Lee, S. Smith, “Yield analysis and data management using Yield ManagerTM”, 1998 IEEE/SEMI Advanced Semiconductor Manufacturing Conference and Workshop, pp. 19-30, 1998.
[4] H. Koyama, M. Inokuchi, “Yield Management for Development and Manufacture of Integrated Circuits”, 1998 IEEE/SEMI Advanced Semiconductor Manufacturing Conference, pp. 208-211, 1998.
[5] G. Ducotey, A. Couvat, V. Audran, D. Pepper, L. Couturier, D. David, “In-line methodology for defectivity analysis from dark field wafer inspection to defect root cause analysis using FIB cut”, 2008 IEEE/SEMI Advanced Semiconductor Manufacturing Conference, pp. 138-141, 2008.
[6] C. F. Chien, W. C. Wang and J. C. Cheng, "Data mining for yield enhancement in semiconductor manufacturing and an empirical study." Expert Systems with Applications 33.1, pp. 192-198, 2007.
[7] A. Chen and A. Hong, "Sample-efficient regression trees (SERT) for semiconductor yield Loss Analysis." IEEE Transactions on Semiconductor Manufacturing, vol. 23, no. 3, August 2010.
[8] C.-K. Ing and T. L. Lai, "A stepwise regression method and consistent model selection for high-dimensional sparse linear models," Statistica Sinica, vol. 21, pp. 1473-1513, 2011.
[9] Trevor Hastie, Robert Tibshirani and Jerome Friedman, “The Elements of Statistical Learning : Data Mining, Inference, and Prediction” , Springer, New York, 2009
[10] F.-T. Cheng, Y.-S. Hsieh, J.-W. Zheng, S.-M. Chen, R.-X. Xiao and C.-Y. Lin, “A Scheme of High-Dimensional Key-Variable Search Algorithms for Yield Improvement,” To appear in IEEE Robotics and Automation Letters, June 2016.
[11] Robert McGill, John W. Tukey and Wayne A. Larsen, “Variations of Box Plots,” The American Statistician, Vol. 32, No. 1, pp. 12-16, 1978.
[12] F.-T. Cheng, C.-A. Kao, C.-F. Chen; W.-H. Tsai, “ Tutorial on Applying the VM Technology for TFT-LCD Manufacturing,” IEEE Transactions on Semiconductor Manufacturing, vol. 28, no. 1, pp. 55-69, 2015.
[13] 田民波，林怡欣校訂，TFT LCD面板設計與構裝技術，五南圖書出版社，2010，第七章。
[14] 蕭宏，半導體製程技術與導論，第三版，全華出版社，2014。
[15] Y.-T. Huang and F.-T. Cheng, “Automatic data quality evaluation for the AVM system,” IEEE Transactions on Semiconductor Manufacturing, vol. 24, no. 3, pp.445-454, August 2011.
[16] F.-T. Cheng, H.-C. Huang, and C.-A. Kao, “Developing an automatic virtual metrology system,” IEEE Transactions on Automation Science and Engineering, vol. 9, no. 1, pp. 181-188., January 2012.
[17] 陳泀潣。2016。適用於關鍵參數搜尋架構之各式資料品質評估機制。碩士論文。台南:成功大學 製造資訊與系統研究所。
[18] F.-T. Cheng, Y.-T. Chen, Y.-C. Su, and D.-L. Zeng, “Evaluating reliance level of a virtual metrology system,” IEEE Trans. on Semiconductor Manufacturing, vol. 21, no. 1, pp. 92-103, February 2008.
[19] 蕭任翔。2016。適用於關鍵參數搜尋架構之信心指標及盲站搜尋演算法。碩士論文。台南:成功大學 製造資訊與系統研究所。