隨著資訊與網路科技的快速發展，雲端運算已成為網際網路運用的新趨勢。企業使用雲端運算服務，除了可以節省自行建置與維護資訊硬體的昂貴成本，也可以建立新的營運模式，以有效增加商業利益。當設備數量龐大時，傳統以網際網路為基礎的設備監控系統即可能面臨計算與儲存能力不足的問題，降低系統的運作效能。為了利用雲端運算的優點改進傳統設備監控系統之缺失，本研究發展了一個雲端建模服務框架及其必要的核心機制，並利用微軟的平台即服務公有雲Windows Azure，建置了一個雲端建模服務系統。經由本系統，許多使用者將得以透過網際網路使用雲端運算強大的計算與儲存能力，建立各式的設備相關推估模型，進而將推估模型下載至設備端，以執行不同的設備監控功能，如錯誤偵測、製造精度推估、剩餘壽命預測等。本研究實際在一個製造工廠中建構一個CNC工具機的製造精度估測系統，並與雲端建模服務系統整合。最後，本論文以數個實驗測試數據展示本雲端建模服務系統的效能，同時也一併探討此一創新的設備監控營運模式可能之效益。

With the rapid development of information and network technology, cloud computing has become a new trend of Internet applications. If enterprises adopt cloud computing services, they not only can save the expensive costs of creating and maintaining information hardware themselves, but also can create novel business models to effectively increase the business benefits. Once the number of equipment becomes large, traditional Internet-based equipment monitoring systems (EMSs) may encounter the problem of computing and storage capability shortage, thereby reducing the system performance. For leveraging the advantages of cloud computing to improve the shortcomings of traditional EMSs, this study develops a cloud-based model creation service (CMCS) framework and its associated core mechanisms. Also, the Microsoft’s Windows Azure, a platform-as-a-service public cloud, is used to construct a CMCS system. By the CMCS system, many users can utilize the powerful computing and storage capacity of cloud computing via the Internet to create various equipment-related conjecture models, which can then be downloaded to the equipment side for performing different equipment monitoring functions, such as fault detection, production precision conjecture, remaining useful life prediction, etc. This study actually constructs a CNC-tool production precision conjecture system that is integrated with the CMCS system in a manufacturing factory. Finally, several experimental test data are used to demonstrate the performance of the proposed CMCS system. Also, the potential benefits of such a novel equipment-monitoring business model are explored.

[1] SEMI (Semiconductor Equipment and Material International). http://www.semi.org/
[2] e-Diagnostics Guidebook, Revision 2.1, 2005. International SEMATECH: http://www.sematech.org/
[3] M.-H. Hung, F.-T. Cheng, and S.-C. Yeh, “Development of a Web-Services-Based e-Diagnostics Framework for Semiconductor Manufacturing Industry,” IEEE Transactions on Semiconductor Manufacturing, Vol. 17, No. 5, pp. 122-135, February 2005.
[4] F.-T. Cheng, 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, Issue 2, pp. 261-272, May 2011.
[5] T.-H. Pan, B.-Q. Sheng, D.S.-H. Wong, and S.-S. Jang, “A Virtual Metrology System for Predicting End-of-Line Electrical Properties Using a MANCOVA Model with Tools Clustering,” IEEE Transactions on Semiconductor Manufacturing, Vol. 7, Issue 2, pp. 187-195, May 2011.
[6] J.V. Ringwood, S. Lynn, G. Bacelli, B. Ma, E. Ragnoli, and S. McLoone, “Estimation and Control in Semiconductor Etch: Practice and Possibilities,” IEEE Transactions on Semiconductor Manufacturing, Vol. 23, No. 1, pp. 87-98, Feb. 2010.
[7] 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, July 2007.
[8] T.-H. Lin, F.-T. Cheng, W.-M. Wu, C.-A. Kao, A.-J. Ye, and F.-C. Chang, “NN-Based Key-Variable Selection Method for Enhancing Virtual Metrology Accuracy,” IEEE Transactions on Semiconductor Manufacturing, Vol. 22, No 1, pp. 204-211, Feb. 2009.
[9] Google Docs Web Site. URL:http://www.google.com/google-d-s/b1.html
[10] 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, Feb. 2008.
[11] Salesforce. URL: http://www.salesforce.com/
[12] P. Mell and T. Grance, “The NIST Definition of Cloud Computing,” Vol 53, Issue 6, National Institute of Standards and Technology, Oct. 2009.
[13] S.-Y. Yang, D.-L. Lee, and K.-Y. Chen, “A New Ubiquitous Information Agent System for Cloud Computing - Example on GPS and Bluetooth Techniques in Google Android Platform,” Electric Information and Control Engineering (ICEICE), pp.1929-1932, May 2011.
[14] J. Li, M. Humphrey, D. Agarwal, K. Jackson, C.V. Ingen, and Y. Ryu, “eScience in the Cloud_A MODIS Statellite Data Reprojection and Reduction Pipeline in Windows Azure Platform,” in Proc. of 2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS), Atlanta, Georgia, USA, pp. 1-10, April 2010.
[15] D. Chappell, “Introduction the Windows Azure,” D. Chappell Web Site. URL:http:// www.davidchappell.com/
[16] C.-C. Liu, 「Virtual Metrology Model Creation Server Design and Implementation,」 Master Thesis, National Cheng Kung University, Tainan, Taiwan, ROC, Aug. 2008.
[17] PDC2010 slides. URL:http://www.dotblogs.com.tw/regionbbs/archive/2010/12/13/vm.role.introduction.and.build.vhd.aspx
[18] Microsoft Windows Azure Web Site. URL:http://www.microsoft.com/windowsazure/features/compute/
[19] Y.-T. Huang and F.-T. Cheng, “Automatic Data Quality Evaluation For the AVM System,” IEEE Transactions on Semiconductor Manufacturing, Vol. 24, No. 3, 2011. (In Press)
[20] Windows Azure Pricing. URL: http://www.microsoft.com/windowsazure/pricing/
[21] 小朱的技術隨手寫. URL:http://www.dotblogs.com.tw/regionbbs/Default.aspx
[22] 小朱，「Windows Azure教戰手扎」，基峯資訊出版社，2010年9月。
[23] 李智樺，「Windows Azure雲端運算開發實戰」，悅知文化，2010年7月。
[24] Windows MSDN Web Site. URL:http://msdn.microsoft.com/en-us/library/gg466226.aspx
[25] S. Zhang, S. Zhang, X. Chen, and S. Wu, “Analysis and Research of Cloud Computing System Instance,” The Second International Conference on Future Networks ( ICFN), Qingdao, China, pp. 88-92, Jan. 2010.
[26] J. Wu, L. Ping, X. Ge, Y. Wang, and J. Fu, “Cloud Storage as the Infrastructure of Cloud Computing,” 2010 International Conference on Intelligent Computing and Cognitive Informatics (ICICCI), Kuala Lumpur , Malaysia, pp. 380-383, June 2010.
[27] A. Li, X. Yang, S. Kandula, and M. Zhang, “ Comparing Public Cloud Providers,” IEEE Internet Computing Magazine, Vol. 15, No 2, pp. 50-53, Mar. 2011.