隨著製造科技的日新月異，生產設備也更趨精密。然而，生產設備常因長時間運轉，導使相關零組件老化或故障，進而降低加工產品的品質。因此，在設備監控系統建構預測能力(如錯誤偵測、製造精度推估、剩餘壽命預測等)以確保生產品質相當重要。本研究將發展一種具備預測能力之通用型設備監控平台，稱為v-Machine (Virtual Machine)。v-Machine主要由(1)資料擷取介面，(2)虛擬機核心(Kernel)，(3)可抽換演算法模組(Pluggable Algorithm Module, PAM)，以及(4)通訊介面等所組成。v-Machine可透過資料擷取介面直接連接裝設於生產設備上的感測器，擷取製造加工時的感測資料。虛擬機核心包含一個資料前處理模組，可以對原始感測資料進行處理與篩選，然後計算出相對應的特徵值 (Indicators)；之後，這些特徵值可用來建立預測模型或是傳給可抽換式演算法模組進行加工參數之預測。可抽換式演算法模組乃是將含有演算法的預測模型建置成可抽換的形式而成。我們可以依照應用的需求，動態地載入v-Machine中。而通訊介面可讓v-Machine透過SOAP協定與外部系統交換資料。最後，本研究將v-Machine實際應用於CNC工具機之加工精度預測。實驗測試結果顯示，v-Machine確實能符合各項功能設計需求，並有不錯之效能。

With the advancement of manufacturing technologies, production equipment has become more sophisticated. However, because production equipment is often in long-term operation, some of its components may become aged or broken, thereby reducing the quality of processed products. Therefore, the construction of a predictive capability (such as fault detection, manufacturing precision conjecture, remaining useful life prediction, etc.) in an equipment monitoring system to ensure production quality is very important. This study develops a generic equipment monitoring platform with prediction functionality, called v-Machine (virtual machine). The v-Machine mainly consists of four parts: (1) data acquisition interface, (2) kernel, (3) pluggable algorithm module (PAM), and (4) communication interface. The v-Machine connects to the sensors on production equipment through the data acquisition interface to acquire sensor data during the manufacturing process. The kernel contains a data pre-process module that can process and filter the raw sensor data and compute the corresponding indicators. Then, these indicator data can be used to create conjecture models or fed to the PAM to forecast the process parameters. The PAM is generated by creating the prediction model in a form with a pluggable interface. We can dynamically download a proper PAM to the v-Machine according to the application need. The communication interface can allow the v-Machine to exchange data with other systems through the SOAP protocol. Finally, this study practically applies the v-Machine to the process precision conjecture of CNC tools. Experimental results show that the v-Machine can really meet all the functional design requirements and has a good performance.

[1] SEMI (Semiconductor Equipment and Material International).
http://www.semi.org/
[2] D.-D. Sheu, “Overall Input Efficiency and Total Equipment Efficiency,” IEEE Transactions on Semiconductor Manufacturing, Vol. 9, No. 4, pp. 496–501, Nov. 2006.
[3] M.-H. Hung, K.-Y. Chen, R.-W. Ho, and F.-T. Cheng, “Development of an e-Diagnostics/Maintenance Framework for Semiconductor Factories with Security Considerations,” Advanced Engineering Informatics, Vol. 17, pp. 165-178, Oct. 2003.
[4] e-Diagnostic and EEC Workshop, International SEMITECH, Austin, Texas, USA, Oct. 19, 2001. [Online]. Available: http://www.semitech.org/
[5] 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, Feb. 2005.
[6] M.-C. Chen, K.-Y. Chen, M.-F. Hsu, and C.-T. Yeh, “A Web Services-Based Collaborative Planning, Forecasting, and Replenishment (CPFR) Framework for Managing Spare Parts of Semiconductor Equipment,” IEEE Transactions on Semiconductor Manufacturing, Vol. 22, No. 4, Nov. 2009.
[7] M-C García, M-A Sanz-Bobi, and D.J. Pico, “SIMAP: Intelligent System for Predictive Maintenance. Application to the Health Condition Monitoring of a Wind-Turbine Gearbox,” Computers in Industry-Special issue: E-maintenance, Vol. 56, No. 6, pp. 552-568, 2006.
[8] Y.-C. Su, “Embedded System Framework Design for Data Collection and Analysis in the Semiconductor and Optoelectronic Industries,” in Proc. of the 4th IEEE Conference on Industrial Electronics and Applications (ICIEA 2009), pp.76-81, May 2009.
[9] M. Mori, M. Fujishima, M. Komatsu, B. Zhao, and Y. Liu, “Development of Remote Monitoring and Maintenance System for Machine Tools,” CIRP Annals- Manufacturing Technology, Vol. 57, No. 1, pp. 433-436, 2008.
[10] Y.-C. Su, F.-T. Cheng, M.-H. Hung, and H.-C. Huang, “Intelligent Prognostics System Design and Implementation,” IEEE Transactions on Semiconductor Manufacturing, Vol. 19, No. 2, May 2006.
[11] S. Gupta, “A Performance Comparison of Windows Communication Foundation (WCF) with Existing Distributed Communication Technologies,” .NET Framework Developer Center Web Site. URL:
http://msdn.microsoft.com/en-us/library/bb310550.aspx#wcfperform_topic3c/
[12] W. Zhang and J. Li, “Research and Application of WCF extensibility,” in Proc. of 2010 International Conference on Web Information Systems and Mining, Vol. 2 pp. 636-367, Jan. 2011.
[13] 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. of 2008 IEEE Conference on Automation Science and Engineering (CASE 2008), Washington DC, USA, pp. 23-26, August 2008.
[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, July 2007.
[15] H.-C. Huang, Y.-C. Su, F.-T. Cheng, and J.-M. Jian, “Development of a Generic Virtual Metrology Framework,” in Proc. of 2007. IEEE International Conference on Automation Science and Engineering (CASE 2007), pp. 22-25, Sept. 2007.
[16] Y.-C. Su, M.-H. Hung, F.-T. Cheng, and T.-P. Lee, “Development of a Data Pre-processing Scheme and Pluggable Application Modules for an Intelligent Equipment Prognostics System,” in Proc. of 2005 IEEE International Conference on Industrial Informatics (INDIN 2005), pp.38-43, August 2005.
[17] F.-T. Cheng, G.-W. Huang, C.-H. Chen, and M.-H. Hung, “A Generic Embedded Device for Retrieving and Transmitting Information of Various Customized Applications,” in Proc. of 2004 IEEE International Conference on Robotics and Automation (ICRA 2004), Vol. 1, pp. 978-983, May 2004.
[18] 洪良德，「精密量測實驗」，高立圖書有限公司，台北市，2006年10月。