目前多數錯誤偵測與診斷及預測保養的方法，是找出關鍵零組件失效模式，萃取出特徵訊號，建立其模型。但由於失效模式有很多種形態，且也無法保證能將所有的失效模式均收集起來，使得無法準確進行錯誤偵測與診斷及預測保養。為解決此一缺失，本篇論文應用虛擬量測技術發展出Baseline Predictive Maintenance機制。虛擬量測(VM)之定義為：『在產品尚未或無法進行實際量測之情況下，利用生產機台參數，推估其所生產之產品品質』。本篇論文應用虛擬量測的技術即時產生機台或關鍵零組件之健康狀態的基準點，並利用一啟發式模型精進演算法來優化預測健康狀態基準點的模型。透過整合來自實際觀測值與預測值之差以及重要參數的變化，訂定出判斷邏輯來實現預測保養及錯誤診斷的目標。

At present, most FDC and PdM approaches are to find out the failure mode of the target device, extract out the characteristic signals, and set up their models. However, there are too many kinds of failure modes to ensure the collection of all of them, thus, FDC and PdM cannot be accurately executed. In order to solve this disadvantage, Virtual Metrology for developing Baseline Predictive Maintenance Mechanism is utilized. Virtual Metrology is defined as “utilizing the equipment parameter data to forecast the quality of products before the products are either not ready or not able to be measured”. In this paper, an approach to predict the healthy baseline of the target device in real-time and utilize a heuristic algorithm to enhance the baseline-predicted model is proposed. By integrating the differences between real measurement and virtual metrology and the variance of key parameters, diagnostic logics are set to realize the goals of PdM and FDC.

參考文獻
[1] ISMI Predictive and Preventive Maintenance Equipment Implementation Guidelines, Technology Transfer #08064934A-ENG International SEMATECH Manufacturing Initiative, August 30, 2008.
[2] ISMI Consensus Preventive and Predictive Maintenance Vision Guideline: Version 1.1 Technology Transfer #06114819C-ENG International SEMATECH Manufacturing Initiative, November 20, 2007.
[3] J. Hollister and P. McGuire, Research on the Current Status of Predictive Maintenance (PdM) Algorithms and Applications, ISMI Predictive and Preventive Maintenance Initiative, Alan Weber and Associates, Inc., February, 2009.
[4] ISMI Predictive Preventive Maintenance Data Requirements International SEMATECH Manufacturing Initiative, September 30, 2009
[5] Predictive Preventive Maintenance Impact on Factory Cost and Cycle Time International SEMATECH Manufacturing Initiative December 31, 2009.
[6] M.-D. Ma, S.-H. Wong, S.-S. Jang, and S.-T. Tseng, "Fault Detection Based on Statistical Multivariate Analysis and Microarray Visualization," IEEE Transactions on Industrial Informatics, vol. 6, no. 1, February 2010.
[7] C. Letellier, G. Hoblos, H. Chafouk, "Robust Fault Detection based on Multimodel and Interval Approach. Application to a Throttle Valve," in Proc.19th IEEE Mediterranean Conference on Control and Automation (MED '11), pp. 479-484, Aquis Corfu Holiday Palace, Corfu, Greece. June 20-23, 2011.
[8] W. Gasta, "Statistical Process Control Using Key Process Indicators for Vacuum Devices, " in Proc. Fifth IEEE International Vacuum Electronics Conference: IEEE IVEC 2004, pp. 109, Monterey, California, USA. April 27-29 2004.
[9] D. Siegel, J. Lee, and C. Ly, "Methodology and Framework for Predicting Rolling Element Helicopter Bearing Failure," in Proc. 2011 IEEE International Conference on Prognostics and Health Management(PHM), pp.1-9, June 20-23 2011
[10] J. Liu, D. Djurdjanovic, J. Ni, N. Casoetto, J. Lee, "Similarity based method for manufacturing process performance prediction and diagnosis, "Computers in Industry, vol. 58 (6), pp.558-566, January 2007.
[11] T. Wang, J. Yu, D. Siegel, and J. Lee, "A Similarity-Based Prognostics Approach for Remaining Useful Life Estimation of Engineered Systems," in Proc. International conference on prognostics and health management, pp.1-6, October 2008
 
[12] S.-J. Wu, N. Gebraeel, M.-A. Lawley, Y. Yih, "A Neural Network Integrated Decision Support System for Condition-Based Optimal Predictive Maintenance Policy," IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, vol. 37, no. 2, pp. 226-236, March 2007.
[13] Z. Tian, M. J. Zuo, "Health Condition Prediction of Gears Using a Recurrent Neural Network Approach," IEEE Transactions on Reliability, vol. 59, no. 4, pp. 700-705, December 2007.
[14] F.-T. Cheng, H.-C. Huang, and C.-A. Kao, "Dual-Phase Virtual Metrology Scheme," IEEE Transactions on Semiconductor Manufacturing, vol. 20, no. 4, pp. 566-571, November 2007.
[15] M.-H. Hung, T.-H. Lin, F.-T. Cheng, and R.-C. Lin, "A Novel Virtual Metrology Scheme for Predicting CVD Thickness in Semiconductor Manufacturing," IEEE/ASME Transactions on Mechatronics, vol. 12, no. 3, pp. 308-316, June 2007.
[16] Y.-C. Su, T.-H. Lin, F.-T. Cheng, and W.-M. Wu, "Accuracy and Real-Time Considerations for Implementing Various Virtual Metrology Algorithms," IEEE Transactions on Semiconductor Manufacturing, vol. 21, no. 3, pp. 426-434, August 2008.
[17] F.-T. Cheng, Y.-T. Chen, Y.-C. Su, and D.-L. Zeng, "Evaluating Reliance Level of a Virtual Metrology System," IEEE Transactions on Semiconductor Manufacturing, vol. 21, no. 1, pp. 92-103, February 2008.
[18] Y.-T. Huang, H.-C. Huang, F.-T. Cheng, T.-S. Liao, and F.-C. Chang, "Automatic Virtual Metrology System Design and Implementation," in Proc. 2008 IEEE International Conference on Automation Science and Engineering, Washington, D.C., U.S.A., pp. 223-229, August 2008.
[19] Y.-T. Huang, 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.
[20] R. L. Mason, R. F. Gunst, and J. L. Hess, Statistical Design and Analysis of Experiments with Applications to Engineering and Science, New York: Wiley, 1989
[21] S. Haykin, “Neural Networks, A Comprehensive Foundation,” Prentice Hall, NJ:07458, 1999.
[22] D. W. Scott, Wiley Interdisciplinary Reviews: Computational Statistics, vol. l, issue 3, pp. 303-306, Nov 2009.
[23] 羅文雄, 蔡榮輝, 鄭岫盈 「半導體製造技術」，滄海書局，2011
[24] 郝平,”電子產品老化時間的簡便計算及程序”,www.cqvip.com.
[25] 蘇育全, “智慧型預測系統設計與實作”, 國立成功大學製造工程研究所博士論文, 2006.