當晶圓的面積增大時，晶圓上的缺陷並非呈現隨機性分布，而是有群聚現 象發生。缺陷群聚現象使得卜瓦松良率模式低估產品的良率；負二項良率模式中 的值過於散亂，也可能為負值；複合卜瓦松良率模式的建構複雜，較不易為業 界所接受。Jun et al. 所建構之良率模式，必需考慮迴歸模型之適配度與基本假 設是否違反；利用倒傳遞網路構建良率模式則需考慮網路參數設定問題。此外，
目前是以人工的方式分析晶圓上缺陷的空間樣式以找出製程變異的可能原因。然 而，人工判定除了費時外，亦可能因誤判進而影響偵測製程變異的準確性。因此，
構建一個有效的晶圓缺陷樣式辨識系統為學界與業界重視。許多文獻提出一些晶 圓缺陷樣式辨識方法來判定製程是否異常，但亦皆有其不完善之處。
本研究利用一般迴歸神經網路(GRNN)來構建良率模式，並利用多類別支撐 向量機(Multi-class SVM)來構建缺陷樣式辨識系統；最後整合成一個良率預估模 式及缺陷樣式辨識之晶圓缺陷診斷系統。本研究以模擬實驗來說明本研究所提之 整合良率預估及缺陷樣式辨識之晶圓缺陷診斷系統的可行性；並進一步與學者所 提之良率預估模式與缺陷樣式辨識系統做比較以驗證本研究的有效性與優越 性。本研究所提之整合良率預估及缺陷樣式辨識之晶圓缺陷診斷系統的優點如 下：
1. 本研究能找到四個切題的晶圓特徵因子(D、CVA、CVD以及 CIE)當作 GRNN 良率預估模式之輸入變數來預估晶圓良率；比其他中外文獻所提的良率模式 只能找到一個或兩個參數來預估晶圓良率有更準確的預估效果。
2. 本研究所提之多類別 SVM 晶圓缺陷樣式辨識系統在本模擬實驗之個案中，
亦比利用 BPNN 網路以及 RBF 神經網路之辨識技術更能夠正確地來辨識晶圓 表面的缺陷樣式。
本研究構建之晶圓缺陷樣式診斷系統未來可與晶圓缺陷檢測掃瞄器 KLA 機 台整合應用於 IC 生產線上。當製程呈現中、低良率時，可即時追蹤發生原因，
以進一步做診斷改善。再者，製程工程師亦可在晶圓完成製造並經由檢測後，藉 由位元圖得到的不良晶片資訊與本研究於每個關鍵製程的診斷做比對，以分析可 能導致該晶片不良的原因，儘速進行改善措施。
參考文獻
[1] 李靜宜，「應用倒傳遞類神經網路構建積體電路之良率模式」，國立交通大學 工業工程研究所碩士論文，2003。
[2] 莊達人，『VLSI 製造技術』，高立，2006。
[3] 許志瑋，「整合缺陷點數與群聚指標之積體電路良率模式」，國立交通大學工 業工程研究所碩士論文，2003。
[4] 楊博欽，「應用自組性演算法建構積體電路之良率模式」，國立交通大學工業 工程研究所碩士論文，2005。
[5] 葉怡成，『類神經網路模式應用與實作』，儒林，2003。
[6] Albin, S.L., Friedman, D.J., “Clustered defects in IC Fabrication: Impact on Process Control Charts.” IEEE Trans. on Semiconductor Manufacturing, Vol. 4, No. 1, pp. 36-42, 1991.
[7] Bhanu, B., Lee, S. and Ming, J., “Adaptive Image Segmentation Using a Genetic Algorithm.” IEEE Transactions on Systems Man Cybernetics, Vol. 25, No. 12, pp.
1543-1567, 1995.
[8] Bottou, L., Cortes, C., Denker, J., Drucker, H., Guyon, I., Jackel, L., LeCun, Y., Muller, U., Sackinger, E., Simard, P. and Vapnik, V., “Comparison of Classifier Methods: A Case Study in Handwritten Digit Recognition.” Proceedings of the International Conference on Pattern Recognition. Los Alamitos, CA : IEEE Computer Society Press, 1994.
[9] Box, G. E. P., Cox, D. R., “An Analysis of Transformations.” Journal of the Royal Statistical Society, Series B, Vol. 26, pp. 211-43, 1964.
[10] Burges, C. J. C., “A Tutorial on Support Vector Machines for Pattern Recognition.” Data Mining and Knowledge Discovery, Vol. 2, No. 2, pp.
121-167, 1998.
[11] Chang, C. C., Lin, C. J., “LIBSVM: A Library for Support Vector Machines.”
2004. http://www.csie.ntu.edu.tw/~cjlin/libsvm/.
[12] Chen, C. L., Chang, M. H., “Optimal Design of Fuzzy Sliding-Mode Control: A Comparative Study.” Fuzzy Sets and Systems, Vol. 93, No. 1, pp. 37-48, 1998.
[13] Cortes, C., Vapnik, V., “Support Vector Networks.” Machine Learning, Vol. 20, No. 3, pp. 273-297, 1995.
[14] Cunningham, J.A., “The Use and Evaluation of Yield Models in Integrated Circuit Manufacturing.” IEEE Trans. on Semiconductor Manufacturing, Vol. 3, No. 2, pp. 60-71, 1990.
[15] David, A., Lerner, B., “Support Vector Machine-based Image Classification for Genetic Syndrome Diagnosis.” Pattern Recognition Letters, Vol. 26, No. 8, pp.
1029-1038, 2005.
[16] Duda, R. O., Hart, P. E., Pattern Classification and Scene Analysis. John Wiley
& Sons, New York, 1973.
[17] Fausett, L., “Fundamentals of Neural Networks Architectures, Algorithms, and Applications.” Prentice Hall, 1994.
[18] Ferris-Prabhu, Alber.V., Introduction to Semiconductor Device Yield Modeling.
Boston : Artech House, 1992.
[19] Fiesler, E., “Comparative Bibliography of Ontogenic Neural Networks.”
Proceedings of the International Conference on Artificial Neural Networks, pp.
793-796, Sorrento, Italy, 1994.
[20] Friedman, D. J., Hansen, M. H., Nair, V. N. and James, D. A., “Model-free Estimation of Defect Clustering in Integrated Circuit Fabrication.” IEEE Transactions on Semiconductor Manufacturing, Vol. 10, No. 3, pp. 344-359, 1997.
[21] Hornick, K., Stinchcombe, M. and White, H., “Universal Approximation of An Unknown Mapping and its Derivatives Using Multilayer Feedforward Networks.” Neural Networks, Vol. 3, No. 5, pp. 551-560, 1990.
[22] Hsu, C. W., Lin, C. J., “A Comparison of Methods for Multi-class Support Vector Machines.” IEEE Transactions on Neural Networks, Vol. 13, No. 2, pp. 415-425, 2002.
[23] Jain, A. K., Duin, R. P. W. and Mao, J., “Statistical Pattern Recognition: A Review.” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.
22, No. 1, pp. 4-37, 2000.
[24] Jiang, S., Huang, Q., Ye, Q. and Gao, W., “An Effective Method to Detect and Categorize Digitized Traditional Chinese Paintings.” Pattern Recognition Letters, Vol. 27, No. 7, pp. 734-746, 2006.
[25] Jun, C.H., Hong, Y., Kim, S.Y., Park, K.S. and Park, H., “A Simulation-based Semiconductor Chip Yield Model Incorporating a New Defect Cluster Index.”
Microelectronics Reliability, Vol. 39, No. 4, pp. 451-456, 1999.
[26] Keerthi, S. S., Lin, C. J., “Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel.” Neural Computation, Vol. 15, No. 7, pp. 1667-1689, 2003.
[27] KreBel, U., “Pairwise Classification and Support Vector Machines.” Advances in kernel methods: Support Vector Learning, pp. 255-268. Cambridge, MA: MIT Press, 1999.
[28] Merino, M. A., Cruceta, S., Garcia, A. and Recio, M., “SmartBitTM: Bitmap to Defect Correlation Software for Yield Improvement.” Advanced Semiconductor Manufacturing Conference and Workshop, 2000 IEEE/SEMI, pp. 194-198.
Boston, MA, 2000.
[29] Murphy, B. T., ”Cost-size Optimum of Monolithic Integrated Circuits.” Proc.
IEEE, Vol. 52, pp. 1537-1545, 1964.
[30] Nemmour, H., and Chibani, Y., “Multiple Support Vector Machines for Land Cover Change Detection: An Application for Mapping Urban Extensions.”
ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 61, No. 2, pp.
125-133, 2006.
[31] Nieddu, L., Patrizi, G., “Formal Methods in Pattern Recognition.” European Journal of Operation Research, Vol. 120, No. 3, pp. 459-495, 2000.
[32] Parzen, E., “On Estimation of a Probability Density Function and Mode.” The Annals of Mathematical Statistics, Vol. 33, No. 3, pp. 1065-1076, 1962.
[33] Platt, J. C., Cristianini, N. and Shawe-Taylor, J., “Large Margin DAGs for Multiclass Classification.” In: Advances in neural information processing systems, pp. 547-553. Cambridge, MA: MIT Press, 2000.
[34] Raghavachari, M., Srinivasan, A. and Sullo, P., “Poisson Mixture Yield Models for Integrated Circuits: A Critical Review,” Microelectronics Reliability, Vol. 37, No. 4, pp. 565-580, 1997.
[35] Schölkopf, B., Smola, A. J., Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. Cambridge, MA: MIT Press, 2002.
[36] Specht, D. F., “A General Regression Neural Network, ”IEEE Transactions on Neural Networks, pp. 568-576, 1991.
[37] Stapper, C. H., and Rosner, R. J., “Integrated Circuit Yield Management and Yield Analysis: Development and Implementation.” IEEE Transactions on Semiconductor Manufacturing, Vol. 8, No. 2, pp. 95-102, 1995.
Statistics,” Proceedings of The IEEE, Vol. 71, pp. 453-470, 1983.
[39] Stapper, C. H., “Defect Density Distribution for LSI Yield Calculations.” IEEE Transaction on Electron Devices (Correspondence), Vol. 20, No. 7, pp. 655-657, 1973.
[40] Stapper, C. H., “The Effects of Wafer to Wafer Defect Density Variations on Integrated Circuit Defect and Fault Distributions.” IBM Journal of Research Development, Vol. 29, No. 1, pp. 87-97, 1985.
[41] Stapper, C. H., “On Murphy’s Yield Integral.” IEEE Trans. on Semiconductor Manufacturing, Vol. 4, No. 4, pp. 294-297, 1991.
[42] Tong, L. I., Lee, W. I. and Su, C. T., “Using a Neural Network-Based Approach to Predict the Wafer Yield in Integrated Circuit Manufacturing.” IEEE Trans. On Components, Packaging, and Manifacturing Technology-Port C, Vol. 20, Iss. 4, pp.288-294, 1997.
[43] Tong, L. I., Wang, C. H. and Chen, D. L., “Development of a New Cluster Index for Wafer Defects.” The International Journal of Advanced Manufacturing Technology, Vol. 31, No. 7-8, pp. 705-715, 2007.
[44] Tsai, W. J., Tong, L. I. and Wang, C. H., “Developing a New Defect Cluster Index.” Journal of the Chinese Institute of Industrial Engineers, Vol. 25, No. 1, pp. 18-30, 2008.
[45] Tyagi, A., Bayoumi, A. M., “Defect Clustering Viewed Through Generalized Poisson Distribution.” IEEE Trans. on Semiconductor Manufacturing, Vol. 5, No.
3, pp. 196-206, 1992.
[46] Tyagi, A., Bayoumi, M. A., “The Nature of Defect Patterns on Integrated-circuit Wafer Maps.” IEEE Transactions on Reliability, Vol. 43, No. 1, pp. 22-29, 1994.
[47] Vapnik, V., Statistical learning theory. New York: Wiley, 1998.
[48] Widrow, B., Winter, R. G. and Baxter, R. A., “Learning Phenomena in Layered Neural Networks.” Proceedings of the First IEEE International Conference on Neural Networks, pp. 411-429. San Diego, 1987.
[49] Zhou, J., Su, G., Jiang, C., Deng, Y. and Li, C., “A face and Fingerprint Identity Authentication System Based on Multi-route Detection.” Neurocomputing, Vol.
70, No. 4-6, pp. 922-931, 2007.