良率的提升對於企業的盈利能力表現至關重要，特別是在研發和大量生產階段。因此，當良率發生問題時，在此階段，應迅速確定良率損失的根本原因，以節省生產成本。為了確定根本原因，傳統良率管理系統蒐集各式與生產相關之資訊，進行大數據分析。然而，由於與生產相關的數據通常龐大且複雜，因此很難快速搜尋影響良率的根本原因。有鑑於此，Cheng等學者 [1]提出適用於良率改善之高維度關鍵參數搜 (A Scheme of High-Dimensional Key-Variable Search Algorithms)尋演算法架構來解決此問題。高維度關鍵參數搜尋演算法架構為使用者提供了一種快速且有效的方法來確定影響良率的根本原因，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。然而，當關鍵製程中關鍵機台與其他影響良率較小之次關鍵機台，倆倆交互作用影響力大於原先之關鍵機台時，如果根本原因是在上述交互作用影響之兩機台中，則高維度關鍵參數搜尋演算法架構不能進行正確的識別。
為解決此困境，本研究參考「使用提高樣本使用效率迴歸樹 (Sample-Efficient Regression Trees)」 [7]架構進行分析，可藉由F檢定提供使用者交互作用機台之顯著程度，並提出適用於關鍵站點搜尋法的『交互作用模組』，藉以輔佐 KSA機制解決因演算法的限制造成機制中之核心演算法運算上產生之盲點。關鍵參數搜尋法為良率管理系統中之一種方法，本論文提出的機制使此方法在執行時能更完善且效益更高。

Yield enhancement is crucial for the companies’ profitability performance, especially during the development and mass production phases. So, the root causes of yield loss should be quickly identified in these stages for saving the production cost. To identify the root causes, traditional yield enhancement approaches collect all production-related data for big data analysis. Nevertheless, since the production-related data are often large and complicated, it is difficult to quickly search for the root causes that affect the yield. In light of this, the Key-variable Search Algorithm (KSA) [1] was proposed to resolve this problem. The KSA scheme provides users a quick and efficient way to identify the root causes of yield. 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. However, when key tool interact with other minor critical tools and both the impact of the interaction is greater than the original key tool, if the root cause is in above two interaction tools, the High-Dimensional Key-Variable Search Algorithms Scheme cannot be correctly identified.
To address this dilemma, this study is based on the SERT [7] architecture to analyze. Through the F-test to provide users with the significance of the interaction, in this paper proposed the "interaction effect module" to enhance the KSA Scheme to solve the limitations of the algorithm caused by the calculation of the core algorithm on the blind spot.

[1] 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", IEEE Robotics and Automation Letters, vol. 2, no. 1, pp. 179-186, Jan. 2017.
[2] R. Vernon, "International investment and international trade in the product cycle", The quarterly journal of economics, vol. 80, pp. 190-207, 1966.
[3] F.-T. Cheng, C.-Y. Lin, C.-F. Chen, R.-X. Xiao, J.-W. Zheng, and Y.-S. Shieh, “Blind-stage Search Algorithm for the Key-variable Search Scheme,” IEEE Robotics and Automation Letters, vol. 2, no. 4, pp.1840-1847, Oct. 2017.
[4] 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.
[5] 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.
[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] R. Tibshirani, "Regression shrinkage and selection via the LASSO", J. Roy. Statist. Soc. B, vol. 58, no. 1, pp. 267–288, 1996.
[10] 張翔，提綱挈領學統計，五版。TKB出版，2014。
[11] C. Neuhauser, " Hypothesis Testing“, Created, November 29, 2009
[12] 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。
[13] 蕭宏，半導體製程技術與導論，第三版，全華出版社，2014。
[14] 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。
[15] 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。
[16] 鄭景文。2017。適用於良率改善之高維度關鍵參數搜尋演算法架構。碩士論文。台南:成功大學 製造資訊與系統研究所。
[17] Breiman, Leo; Friedman, J. H., Olshen, R. A., & Stone, C. J. "Classification and regression trees", Monterey, CA, Wadsworth & Brooks/Cole Advanced Books & Software, 1984.