當半導體正式進入奈米製程世代，且因應全球市場對於資訊電子產品傾向輕、薄、短、小的特性與高速化及高性能化的急遽發展，迫使半導體公司致力於縮小晶片內電路線之寬度，以獲得全球半導體產業競爭優勢，使得半導體製程更為複雜冗長、影響變數更多以及技術門檻愈來愈高。為克服製程技術不斷衍生的物理極限，半導體設備發展出各項精密感測器達成各種即時監控與偵測系統來提升晶圓良率與生產效率，但是並非所有半導體設備零件皆適用於裝載感測器來避免產出具缺陷的低良率晶圓。因此，本研究應用資料探勘技術來結合無感測器偵測所導致的晶圓缺陷特徵與其晶圓量測資料，據以建構一套晶圓缺陷偵測模型，並整合時間序列模型以預測未來零件發生變異之趨勢，進而發展出半導體零件變異預測模型，以利實現智慧製造系統之即時反饋零件生產狀態，達成長期監控以及預測與評估零件變異徵兆，來有效避免零件變異所衍發的大量晶圓良率損失問題。本研究論文最後將透過半導體覆晶封裝之凸塊製程的實例研究，闡明本研究模型之各項結構，如資料變數彙整與處理過程、晶圓缺陷分析與驗證、資料探勘建模與配適過程以及時間序列分析與ARIMA模型之應用，且經由實例成果證實本研究模型能夠有效地評估無感測器之半導體零件變異徵兆，並能準確地預測未來變異之趨勢，以排除量產前的預檢修成本與妥善評估零件檢修最佳時機，進而提升半導體設備整體效率、穩定晶圓良率以及節省半導體整體製造成本。

The study constructs a non-sensor semiconductor components variation prediction model, in which a data-mining framework is proposed based on clustering and decision-tree methods to mine solder bumps of flip-chip package measurement data and defect rates with variation patterns of wafers from huge databases, and thus formulate defect characteristics. This study uses the Principal Component Analysis (PCA) to develop a health index for identifying variations in semiconductor components over time. We also use the ARIMA model to obtain signs of variations, predict future variations in components, and ensure the timing for components maintenance. The obtained results show that the proposed model can successfully predict the components variation trends, reduce the consumption of manpower and production time, effectively enhance the quality and production capacity of wafers, and decrease the overall semiconductor manufacturing costs.

Amato, F., Lopez, A., et al. (2013). Artificial neural networks in medical diagnosis. Journal of applied biomedicine. 11(2), 47-58.
Asghar, S., & Iqbal, K. (2009). Automated data mining techniques: a critical literature review. In 2009 International Conference on Information Management and Engineering. (pp. 75-79) IEEE.
Baek, K. H., Edgar, T. F., et al. (2014). An effective procedure for sensor variable selection and utilization in plasma etching for semiconductor manufacturing. Computers & Chemical Engineering. 61, 20-29.
Bandalos, D. L., & Boehm-Kaufman, M. R. (2009). Four common misconceptions in exploratory factor analysis. Statistical and methodological myths and urban legends: Doctrine, verity and fable in the organizational and social sciences. 61-87.
Boozarjomehry, R., & Svrcek, W. (2001). Automatic design of neural network structures. Computers & Chemical Engineering. 25(7), 1075-1088.
Boucher, X., Le Riche, R., et al. (2013). Semiconductor yield loss' causes identification: A data mining approach. In 2013 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM). (pp. 843-847) IEEE.
Braha, D., & Shmilovici, A. (2002). Data mining for improving a cleaning process in the semiconductor industry. IEEE Transactions on Semiconductor Manufacturing. 15(1), 91-101.
Burkom, H., & Murphy, S. P. (2007). Automated time series forecasting for biosurveillance. Statistics in Medicine, Forthcoming. 06-035.
Chien, C. F., & Chen, L.-F. (2007). Using rough set theory to recruit and retain high potential talents for semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing. 20(4), 528-541.
Chien, C. F., Chen, S. L., et al. (2002). Using Bayesian network for fault location on distribution feeder. IEEE Transactions on Power Delivery. 17(3), 785-793.
Chien, C. F., Chen, Y. J., et al. (2010). Manufacturing intelligence for semiconductor demand forecast based on technology diffusion and product life cycle. International Journal of Production Economics. 128(2), 496-509.
Chien, C. F., & Chuang, S. C. (2014). A Framework for Root Cause Detection of Sub-Batch Processing System for Semiconductor Manufacturing Big Data Analytics. IEEE Transactions on Semiconductor Manufacturing. 27(4), 475-488.
Chien, C. F., Diaz, A. C., et al. (2014). A data mining approach for analyzing semiconductor MES and FDC data to enhance overall usage effectiveness (OUE). International Journal of Computational Intelligence Systems. 7, 52-65.
Chien, C. F., Wang, W. C., et al. (2007). Data mining for yield enhancement in semiconductor manufacturing and an empirical study. Expert Systems with Applications. 33(1), 192-198.
Chow White, P. A., & Green Jr, S. (2013). Data Mining Difference in the Age of Big Data: Communication and the social shaping of genome technologies from 1998 to 2007. International Journal of Communication. 7, 28.
Demchenko, Y., Grosso, P., et al. (2013). Addressing big data issues in scientific data infrastructure. In 2013 International Conference on Collaboration Technologies and Systems (CTS). (pp. 48-55) IEEE.
Despagne, F., & Massart, D.-L. (1998). Variable selection for neural networks in multivariate calibration. Chemometrics and intelligent laboratory systems. 40(2), 145-163.
Evans, S., Lemon, S. J., et al. (1997). Automated detection of hereditary syndromes using data mining. Computers and biomedical research. 30(5), 337-348.
Fu, T. C. (2011). A review on time series data mining. Engineering Applications of Artificial Intelligence. 24(1), 164-181.
Gao, S. (2005). New technologies for lead-free flip chip assembly. (Doctoral dissertation, University of London).
George, G., Haas, M. R., et al. (2014). Big data and management. Academy of Management Journal. 57(2), 321-326.
Gerber, M., Beddingfield, C., et al. (2011). Next generation fine pitch cu pillar technology—enabling next generation silicon nodes. In Electronic Components and Technology Conference (ECTC), 2011 IEEE 61st (pp. 612-618) IEEE.
Ghosh, S., & Maiti, J. (2014). Data mining driven DMAIC framework for improving foundry quality–a case study. Production Planning & Control. 25(6), 478-493.
Harding, J., Shahbaz, M., et al. (2006). Data mining in manufacturing: a review. Journal of Manufacturing Science and Engineering. 128(4), 969-976.
He, Q. P., & Wang, J. (2007). Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes. IEEE Transactions on Semiconductor Manufacturing. 20(4), 345-354.
Hilbert, M., & López, P. (2012). How to measure the world’s technological capacity to communicate, store and compute information? Part I: Results and scope. International Journal of Communication. 6, 956-979.
Hsu, S. C., & Chien, C. F. (2007). Hybrid data mining approach for pattern extraction from wafer bin map to improve yield in semiconductor manufacturing. International Journal of Production Economics. 107(1), 88-103.
Jacobs, A. (2009). The pathologies of big data. Communications of the ACM. 52(8), 36-44.
Koh, W., Lin, B., et al. (2011). Copper pillar bump technology progress overview. In 2011 12th International Conference on Electronic Packaging Technology and High Density Packaging (ICEPT-HDP) (pp. 1-5) IEEE.
Kusiak, A. (2001). Rough set theory: a data mining tool for semiconductor manufacturing. IEEE Transactions on Electronics Packaging Manufacturing. 24(1), 44-50.
Lakshmi, B., & Raghunandhan, G. (2011). A conceptual overview of data mining. In 2011 National Conference on Innovations in Emerging Technology (pp. 27-32) IEEE.
Laney, D. (2014). 3D data management: Controlling data volume, velocity and variety, 2011. Availabl e: http://blogs.gartner. com/doug-laney/files/2012/01/ad949-3D-Data-Manag
ement-Controlling-Data-Volume-Velocity-and-Variety.pdf.
Lau, J. H. (1996). Flip chip technologies: McGraw-Hill Professional.
Lee, N. C. (1999). Lead-free soldering - Where the world is going. Advancing microelectronics. 26(5), 29-35.
Lee, N. C. (2002). Reflow soldering processes and troubleshooting: SMT, BGA, CSP, and flip chip technologies: Newnes.
Lee, U. H., Cho, M., et al. (2013). A Study of Adopting Pure Tin Solder to Pillar Bump. In Meeting Abstracts (pp. 2065-2065) The Electrochemical Society.
Lewis, C. D. (1982). Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting: Butterworth-Heinemann.
Li, Z. G., Baseman, R. J., et al. (2014). A Unified Framework for Outlier Detection in Trace Data Analysis. IEEE Transactions on Semiconductor Manufacturing. 27(1), 95-103.
Lim, G. T., Kim, B. J., et al. (2009). Temperature effect on intermetallic compound growth kinetics of Cu pillar/Sn bumps. Journal of electronic materials. 38(11), 2228-2233.
Lin, J., Keogh, E., et al. (2005). Visualizing and discovering non-trivial patterns in large time series databases. Information visualization. 4(2), 61-82.
Lin, T. H., Kaminski, N., et al. (2008). Alignment and classification of time series gene expression in clinical studies. bioinformatics. 24(13), i147-i155.
Liu, C. W., & Chien, C. F. (2013). An intelligent system for wafer bin map defect diagnosis: An empirical study for semiconductor manufacturing. Engineering Applications of Artificial Intelligence. 26(5), 1479-1486.
Manyika, J., Chui, M., et al. (2011). Big data: The next frontier for innovation, competition, and productivity.
Moyne, J., Samantaray, J., et al. (2015). Big data emergence in semiconductor manufacturing advanced process control. In Advanced Semiconductor Manufacturing Conference (ASMC), 2015 26th Annual SEMI (pp. 130-135) IEEE.
Neri, F. (2012). An introduction to the special issue on computational techniques for trading systems, time series forecasting, stock market modeling, and financial assets modeling. WSEAS Transactions on Systems. 11(12), 659-660.
Olden, J. D., & Jackson, D. A. (2002). Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks. Ecological Modelling. 154(1), 135-150.
Ooi, M. P.-L., Joo, E. K. J., et al. (2011). Getting more from the semiconductor test: Data mining with defect-cluster extraction. IEEE Transactions on Instrumentation and Measurement. 60(10), 3300-3317.
Ouyang, R., Ren, L., et al. (2010). Similarity search and pattern discovery in hydrological time series data mining. Hydrological processes. 24(9), 1198-1210.
Padhy, N., Mishra, D., et al. (2012). The survey of data mining applications and feature scope. arXiv preprint arXiv:1211.5723.
Pecht, M. (1994). Integrated circuit, hybrid, and multichip module package design guidelines: a focus on reliability: John Wiley & Sons.
Pecht, M. (2014). Review of high lead solder and lead glass rohs exemption.
Saeys, Y., Inza, I., et al. (2007). A review of feature selection techniques in bioinformatics. bioinformatics. 23(19), 2507-2517.
Sharma, A., & Panigrahi, P. K. (2013). A review of financial accounting fraud detection based on data mining techniques. arXiv preprint arXiv:1309.3944.
Simpson, G. L., & Birks, H. J. B. (2012). Statistical learning in palaeolimnology Tracking environmental change using lake sediments (pp. 249-327): Springer.
Song, H., & Li, G. (2008). Tourism demand modelling and forecasting—A review of recent research. Tourism Management. 29(2), 203-220.
Thomassey, S. (2010). Sales forecasts in clothing industry: the key success factor of the supply chain management. International Journal of Production Economics. 128(2), 470-483.
Tian, Z. G., & Zuo, M. J. (2010). Health Condition Prediction of Gears Using a Recurrent Neural Network Approach. IEEE Transactions on Reliability. 59(4), 700-705.
Tsukahara, H., Nishiyama, Y., et al. (1995). High-speed 3D inspection system for solder bumps. In Photonics East'95 (pp. 168-177) International Society for Optics and Photonics.
Tsung-Nan, T. (2012). Development of a soldering quality classifier system using a hybrid data mining approach. Expert Systems with Applications. 39(5), 5727-5738.
Wirth, R., & Hipp, J. (2000). CRISP-DM: Towards a standard process model for data mining. In Proceedings of the 4th International Conference on the Practical Applications of Knowledge Discovery and Data Mining (pp. 29-39) Citeseer.
Wolff, J. G. (2014). Big data and the SP theory of intelligence. Access, IEEE. 2, 301-315.
Wood, J., Soler, V., et al. (2014). Automated inspection and metrology for 2.5 D and 3D/TSV process assurance. In Electronic Components and Technology Conference (ECTC), 2014 IEEE 64th (pp. 1606-1609) IEEE.
Wu, X. (2000). Building intelligent learning database systems. AI magazine. 21(3), 61.
Wu, X., Zhu, X., et al. (2014). Data mining with big data. IEEE Transactions on Knowledge and Data Engineering. 26(1), 97-107.
Yu, Z., Liang, Y., et al. (2011). Towards a smart campus with mobile social networking. In Internet of Things (iThings/CPSCom), 2011 International Conference on and 4th International Conference on Cyber, Physical and Social Computing (pp. 162-169) IEEE.
Zhang, F., & Liang, H. (2014). Data Mining Based Analysis Method for Chinese Elders' Survival Self-Evaluation in Universal Design. In 2014 Sixth International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC) (pp. 202-205) IEEE.
Zhong, S., Khoshgoftaar, T. M., et al. (2007). Clustering-based network intrusion detection. International Journal of reliability, Quality and safety Engineering. 14(02), 169-187.