目前全自動虛擬量測在鋁輪圈加工自動化產線上並成功實作出了輪圈的中心孔、PCD、平面度、與外徑等尺寸精度項目之預測。然而，由於鋁圈胚料的變異與加工的異常，除可能造成機台或鋁圈的異常撞擊情況之外，亦有加工品質如表面粗度不良與質量不平衡問題。因此，如何因應上述問題，為自動化產線進一步智能化的挑戰。
本研究開發三大模組，分別為預防加工激烈碰撞模組、表面粗糙度預測模組、與動平衡檢測模組等。其中，預防加工激烈碰撞模組可根據不同鋁輪圈特性自動調整碰撞門檻，偵測加工過程的電流異常情況，以停止加工來避免機台發生激烈碰撞或工件的過切問題。而表面粗糙度預測模組與動平衡檢測模組，則為運用關鍵振動與電流感測特徵，結合AVM系統預測功能，提供輪圈表面粗糙度與動平衡的估測結果。
在實驗成果上，預防加工激烈碰撞模組可於0.1秒內偵測到異常加工並停止機台進給。表面粗糙度預測模組可達到輪圈面粗度的平均預測絕對誤差與最大誤差分別為0.2 μm 與1 μm 以下，而動平衡檢測模組可達到平均預測絕對誤差與最大誤分別小於2.5 g 與5.3 g。因此，本研究所提出之模組將可強化AVM系統以適用於輪圈加工自動化與智能化之需求。

So far, Automatic Virtual Metrology has been successfully implemented in the wheel machining automation (WMA) on the center hole rim, pitch circle diameter (PCD), flatness, outer rim diameter, and other accuracy inspection items. This paper works toward making the AVM system more applicable and intelligent in the WMA industry. For instance, the collision avoidance module is used to prevent the tools from severe collision or tool overcutting by detecting processing signals in real time and ceasing the manufacturing when abnormality is found. The wheel surface roughness prediction and dynamic balance detection modules can reduce the metrology cost and damages caused by contacting the workpieces with AVM’s capability of online and real-time total inspection.
Experiment results indicate that the collision avoidance module is able to detect abnormality within 0.1 second down time and stop proceeding. This module can not only automatically adjust the collision threshold, but also successfully expand the AVM application level. With the tolerance of 1μm max error, the wheel surface roughness module is capable to make the mean absolute error (MAE) in 0.2μm. In addition, the wheel dynamic balance module controls the mean absolute error under 2.5g while the max error could be 5.3g. In sum, these three value-added functional modules are proven with the experiment results that they can effectively enhance the intelligence of the processing machine tools.

[1] Haw-Ching Yang, Hao Tieng, and Fan-Tien Cheng, “Automatic Virtual Metrology for Wheel Machining Automation”, International Journal of Production Research., pp. 6367-6377, Nov. 2015.
[2] Cheng, F.-T., H.-C. Huang, and C.-A. Kao, “Dual-Phase Virtual Metrology Scheme”, IEEE Transactions on Semiconductor Manufacturing, vol. 20, no. 4, Nov. 2007.
[3] Cheng, F.-T., H.-C. Huang, and C.-A. Kao, “Developing an Automatic Virtual Metrology System.” IEEE Transactions on Automation Science and Engineering, vol. 9, no 1, Jan. 2012.
[4] Cheng, F.-T., C.-A. Kao, C.-F. Chen, and W.-H. Tsai. 2015.“Tutorial on Applying the VM Technology for TFT-LCD Manufacturing”.” IEEE Transactions on Semiconductor Manufacturing vol. 28, no. 1, Feb. 2015.
[5] Haw-Ching Yang, Hao Tieng, and Fan-Tien Cheng, “Total Precision Inspection of Machine Tools with Virtual Metrology”, IEEE International Conference on Automation Science and Engineering (CASE), Aug. 2015
[6] Ryo Koike, Yasuhiro Kakinuma, Tojiro Aoyama, Kouhei Ohnishi, “ Tool collision detection in high-speed feeding based on disturbance observer”, International Conference on High Performance Cutting, pp. 478-483, 2014.
[7] R.-S. Lin, R.-G. Chang, J.-L. Yan, and H.-S. Chiu, “ An Efficient Algorithm for Collision Detection on Five-Axis Machining”, Applied Mechanics and Materials, vol. 328, pp. 158-162, 2013
[8] M.F.F. Ab. Rashid and M.R. Abdul Lani, "Surface Roughness Prediction for CNC Milling Process using Artificial Neural Network", Proceedings of the World Congress on Engineering, no. 3, June, 2010.
[9] Sebahattin Tiryaki, Abdulkadir Malkoçoglu, Sükrü Özsahin, “Using artificial neural networks for modeling surface roughness of wood in machining process”, Construction and Building Materials, pp. 329-335, no. 66, Sep. 2014.
[10] Luciane Agnoletti S. Pedotti, Ricardo Mazza Zago, Fabiano Fruett, "Instrument Based on MEMS Accelerometer for Vibration and Unbalance Analysis in Rotating Machines", IEEE International Symposium on Instrumentation Systems, Circuits and Transducers (INSCIT), Sep. 2016
[11] Sanjay Taneja, "The Effect of Unbalance on Bearing Life", IOSR Journal of Mechanical and Civil Engineering (IOSRJMCE), vol.1, no.2, pp.47-54, July 2012
[12] Fan-Tien Cheng, Hao Tieng, Haw-Ching Yang, Min-Hsiung Hung, Yu-Chuan Lin, Chun-Fan Wei, Zih-Yan Shieh, “Industry 4.1 for Wheel Machining Automation" IEEE Robotics and Automation Letters, vol. 1, no.1, Jan. 2016
[13] 丁顥。2015。運用全自動虛擬量測於工具機產業之加工精度全檢機制。博士論文。台南:成功大學 製造資訊與系統研究所。
[14] 楊逸群。2014具備全自動虛擬量測功能的鋁輪圈加工自動化系統。碩士論文。台南:成功大學 製造資訊與系統研究所。
[15] 張尹碩。2016。應用全自動虛擬量測於工具機產業。碩士論文。台南:成功大學 製造資訊與系統研究所。
[16] 林亭妤。2015。以模型為基的特徵萃取法提升虛擬量測精度。碩士論文。台南:成功大學 製造資訊與系統研究所。
[17] 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。碩士論文。台南:成功大學 製造資訊與系統研究所。