現今全自動虛擬量測(Automatic Virtual Metrology, AVM)已廣泛地運用在高科技產業及工具機產業之產品檢測，以實現即時線上全檢之目的。而在工具機產業中全廠導入AVM仍有許多待改善的議題，其中，首先面臨最大的挑戰是如何自動建出最適模型，因建模過程步驟繁瑣且建模門檻高，須具備演算法及統計的專業知識。對於工具機業者來說，光是建立模型就會耗費許多人力及時間。為改善上述問題，必須能自動建立出最適模型，本研究從建模前的資料前處理開始，一直到整個建模流程訂定了三項主題來做深入探討，順序分別是:一、最適加工訊號擷取，二、自動建模，三、模型管理。其中，最適加工訊號擷取主要探討資料前處理步驟中，如何找到真正有效加工訊號區間，以提升AVM的精度預測，進而產生更精準的模型供後續建模使用。而自動建模(Automated Model Creation, AMC)則與通用型全自動虛擬量測系統(GED-plus-AVM System, GAVM)做結合，省去許多繁瑣的建模步驟，以及利用演算法自動找出各量測項目所對應之最恰當模型。再來就是突破過去的建模觀點，以全廠觀來檢視的模型管理，不僅針對全廠的模型做監控管理，還設計了一套模型更換機制且訂定模型之新鮮度指標及燈號，透過網頁呈現的方式讓使用者對於模型的狀態一目了然，隨時可進行模型更換的動作，達到管理全廠模型的最終目的。

Nowadays, Automatic Virtual Metrology (AVM) has been widely used in the high-tech industry and the machine tool industry to achieve online real-time inspection. However, there are still many issues to be improved in the AVM implementation of the machine tool industry. One of the biggest challenges is how to build an optimal model automatically. As the modeling processes are complicated with higher standards, and algorithm and statistical expertise are required, it takes a lot of manpower and time for model creation in the machine tool industry. In order to resolve the problems mentioned above to automatically build an optimal model, three major topics starting from the pre-modeling data pre-processing to the whole modeling process are discussed in depth in this research: 1) optimal processing signal acquisition , 2) Automated Model Creation (AMC), and 3) model management. Among them, the optimal processing signal acquisition mainly deals with the issue on how to find out the effective machining signals in data pre-processing to enhance the AVM accuracy for more accurate model creation. Then Automated Model Creation (AMC) is integrated with GED-plus-AVM System (GAVM) to simplify the model creation processes, and algorithms are utilized to find out the most appropriate model for each measurement item. Moreover, factory-wide model management is adopted by developing a model changing mechanism and setting the indicators and light signals of model freshness. Through the webpage interface, not only that users can see the model status at a glance, but model replacement can also be performed at any time to achieve the ultimate goal of managing the factory-wide models.

[1]王國維(2016):適用於工具機產業之全自動虛擬量測系統自動建模機制。國立成功大學製造資訊與系統研究所碩士論文。
[2]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.
[3]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.
[4]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.
[5]T.-H. Lin, F.-T. Cheng, W.-M. Wu, C.-A. Kao, A.-J. Ye, and F.-C. Chang, "NN-based Key-variable Selecting Method for Enhancing Virtual Metrology Accuracy," IEEE Transactions on Semiconductor Manufacturing, vol. 22, no. 1, pp. 204-211, February 2009..
[6]W.-M. Wu, F.-T. Cheng, T.-H. Lin, D.-L. Zeng, and J.-F. Chen, "Selection Schemes of Dual Virtual-Metrology Outputs for Enhancing Prediction Accuracy," IEEE Transactions on Automation Science and Engineering, vol. 8, no. 2, pp. 311-318, April 2011.
[7]F.-T. Cheng, J. Y.-C. Chang, H.-C. Huang, C.-A. Kao, Y.-L. Chen, and J.-L. Peng," Benefit Model of Virtual Metrology and Integrating AVM into MES,“ IEEE Transactions on Semiconductor Manufacturing, vol. 24, no. 2, pp. 261-272, May 2011.
[8]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.
[9]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.
[10]W.-M. Wu, F.-T. Cheng, and F.-W. Kong, "Dynamic-Moving-Window Scheme for Virtual-Metrology Model Refreshing," IEEE Transactions on Semiconductor Manufacturing, vol. 25, no. 2, pp. 238-246, May 2012.
[11]M.-H. Hung, C.-F. Chen, H.-C. Huang, H.-C. Yang, and F.-T. Cheng, "Development of an AVM System Implementation Framework, "IEEE Transactions on Semiconductor Manufacturing, vol. 25, no. 4, pp. 598-613, November 2012.
[12]Y.-S. Hsieh, F.-T. Cheng, H.-C. Huang, C.-R. Wang, S.-C. Wang, and H.-C. Yang, "VM-based Baseline Predictive Maintenance Scheme," IEEE Transactions on Semiconductor Manufacturing, vol. 26, no. 1, pp. 132-144, February 2013.
[13]H.-C. Yang, H. Tieng, and F.-T. Cheng, "Total Precision Inspection of Machine Tools with Virtual Metrology," Journal of the Chinese Institute of Engineers, DOI: 10.1080/02533839.2015.1091279, published online: Oct 2015.
[14]H.-C. Yang, H. Tieng, and F.-T. Cheng, "Automatic Virtual Metrology for Wheel Machining Automation," International Journal of Production Research, Nov 2015.
[15]Y.-C. Lin; M.-H. Hung; H.-C. Huang; C.-C. Chen; H.-C. Yang; Y.-S. Hsieh; F.-T. Cheng, " Development of Advanced Manufacturing Cloud of Things (AMCoT)—A Smart Manufacturing Platform", 2017.
[16]F.-T. Cheng, H.-C. Huang, and C.-A. Kao. 2012. "Developing an Automatic Virtual Metrology System." IEEE Transactions on Automation Science and Engineering 9 (1): 181-188. doi:10.1109/TASE.2011.2169405.
[17]R. Kieser, P. Reynisson, T. J. Mulligan 2005. "Definition of signal-to-noise ratio and its critical role in split-beam measurements." ICES Journal of Marine Science, Volume 62, Issue 1, 1 January 2005, Pages 123–130
[18]J. Horkoff, E. Yu, "Analyzing Goal Models – Different Approaches and How to Choose Among Them",SAC11'11°Proceedings of the 2011 ACM Symposium on Applied Computing Pages 675-682°