面對全球飲料與瓶裝水市場正在快速成長，飲料與瓶裝水包裝業者對於 PET 吹瓶機之需求量大增。不同地區之消費者有不同的需求和習慣，所以機台製造商為了因應消費者各式各樣之需求與成本考量等因素，必須建置不同的吹瓶機機種，提供給世界各地的客戶選擇。然而，吹瓶機在如此高產能生產需求下，如何提供即時且線上自動品質檢測與智慧化生產功能，輔助使用者達到吹瓶製程最佳化以及品質穩定為實務之挑戰。
本研究將導入發展符合吹瓶機製程之雲端AVM (Automatic Virtual Metrology)系統以及基於AVM技術之雲端逐件控制 (Run-to-Run, R2R Control)系統，以便能針對吹瓶機生產之瓶身品質進行線上估測，並針對製程資料與瓶身品質進行大數據資料收集與分析，將原離線且具延遲特性之品質抽檢，轉變為線上且即時之品質全檢，再透過 AVM 計算出之精度預測結果與信心指標回饋給 R2R 系統，讓 R2R 系統可自動調整機台參數值，使製程可獲得即時的調適與修正，提升製程能力20%以上。

Due to the rapid market growth of global beverage and bottled water, the requests on PET blow molding machines from beverage and bottled water manufacturers are increasing. Customers in different areas have various requirements, to respond to all kinds of customer requests and cost considerations, diverse blow-molding machine types should be available for the customers all over the world to choose from. Under such high-capacity production demands, how to provide online and real-time total product inspection and intelligent manufacturing functions to help users reach blow-molding process optimization with stable quality is yet another big challenge.
To solve the problems mentioned above, this research develops cloud-based Automatic Virtual Metrology (AVM) system and AVM-based cloud run-to-run (R2R) control scheme. Big-data collection of process data and bottle quality data will be conducted for the AVM system to change the offline sampling inspection with metrology delay into online and real-time total inspection. Moreover, the R2R control scheme adopts prediction results and reliance indexes generated by AVM for automatic recipe-adjustment calculation such that the center-of-mass of PET bottles can be adjusted promptly with more than 20 % enhancement.

[1] Y. Lin, M. Hung, H. Huang, C. Chen, H. Yang, Y. Hsieh and F. Cheng, “Development of advanced manufacturing cloud of things (AMCoT) – A smart manufacturing platform,” in IEEE Robotics and Automation Letters, vol. 2, no. 3, pp. 1809–1816, Jul. 2017.
[2] F. Cheng, H. Huang and C. Kao, "Developing an Automatic Virtual Metrology System," in IEEE Transactions on Automation Science and Engineering, vol. 9, no. 1, pp. 181-188, Jan. 2012.
[3] H.-C. Huang, Y.-C. Lin, M.-H. Hung, C.-C. Tu, F.-T. Cheng, Development of cloud based automatic virtual metrology system for semiconductor industry, Robotic Computer-Integrated Manufacturing, vol. 34, pp.30–43, 2015.
[4] F.-T. Cheng, C.-A. Kao, C.-F. Chen, W.-H. Tsai, “Tutorial on applying the VM technology for TFT-LCD manufacturing,” in IEEE Trans. Semicond. Manuf., vol.28, no.1,55–69, 2015.
[5] H. Tieng, H.-C. Yang, M.-H. Hung, and F.-T. Cheng, “A novel virtual metrology scheme for predicting machining precision of machine tools,” in Proc. IEEE Int. Conf. Rob. Autom. (ICRA’13), Karlsruhe, Germany, May 6–10, 2013, pp. 264–269.
[6] F. Cheng, H. Tieng, H. Yang, H. Huang, Y. Lin, C. Wei and Z. Shieh, “Industry 4.1 for wheel machining automation,” in IEEE Robot. Autom. Lett., vol. 1, no. 1, pp. 332–339, Jan. 2016.
[7] H. Tieng, T. Tsai, C. Chen, H. Yang, J. Huang and F. Cheng, "Automatic Virtual Metrology and Deformation Fusion Scheme for Engine-Case Manufacturing," IEEE Robotics and Automation Letters, vol. 3, no. 2, pp. 934-941, April 2018.
[8] F.-T. Cheng and Y.-C. Chiu, “Applying the automatic virtual metrology system to obtain tube-to-tube control in a PECVD tool,” IIE Trans., vol. 45, no. 5, pp. 671–682, Jun. 2013.
[9] C. Kao, F. Cheng, W. Wu, F. Kong and H. Huang, "Run-to-Run Control Utilizing Virtual Metrology With Reliance Index," in IEEE Transactions on Semiconductor Manufacturing, vol. 26, no. 1, pp. 69-81, Feb. 2013.
[10] S. Ramli, M. Mustafa, D. Wahab and A. Hussain, "Plastic bottle shape classification using partial erosion-based approach," International Colloquium on Signal Processing & its Applications, pp. 1-4, 2010.
[11] B. Huang, S. Ma, P. Wang, H. Wang, J. Yang, X. Guo, W. Zhang and H. Wang, “Research and Implementation of Machine Vision Technologies for Empty Bottle Inspection Systems,” International Journal Engineering Science and Technology, vol. 21, no 1, pp. 159-169, 2018.
[12] X. Zhou, Y. Wang, C. Xiao, Q. Zhu, X. Lu, H. Zhang, J. Ge and H. Zhao, "Automated Visual Inspection of Glass Bottle Bottom With Saliency Detection and Template Matching," IEEE Transactions on Instrumentation and Measurement, pp. 1-15, 2019. DOI : 10.1109/TIM.2018.2886977
[13] K. Tahboub, I. Rawabdeh, "A design of experiments approach for optimizing an extrusion blow molding process," Journal of Quality in Maintenance Engineering, vol. 10 no. 1, pp.47-54. 2004.
[14] J.-C. ,Yu, X.-X. , Chen, T.-R. Hung and F. Thibault, "Optimization of Extrusion Blow Molding Processes using Soft Computing and Taguchi’s Method," Journal of Intelligent Manufacturing, vol. 15, pp. 625-634. 2004.
[15] N. Zhou, J. W. Pierre and J. F. Hauer, "Initial results in power system identification from injected probing signals using a subspace method," IEEE Transactions on Power Systems, vol. 21, no. 3, pp. 1296-1302, Aug. 2006.
[16] I. Kamwa and R. Grondin, "Fast adaptive schemes for tracking voltage phasor and local frequency in power transmission and distribution systems," IEEE Transactions on Power Delivery, vol. 7, no. 2, pp. 789-795, April 1992.