輪圈加工已朝向全自動化之趨勢整合，然由於典型線上量測方法易造成加工稼動率的損失，目前加工檢查仍以離線量測為主。本研究討論如何導入全自動化虛擬量測(Automatic Virtual Metrology, AVM)於輪圈自動化系統中。在架構上，首先探討導入AVM系統所需的軟硬體，其次說明AVM系統與輪圈加工自動化系統之間的相關配置。在程序上，分析整合AVM系統於輪圈加工自動化系統的流程，並說明其詳細方法。在比較上，更應用模擬軟體FlexSim以模擬導入AVM系統前後多重輪圈加工線的整體效益分析。實際案例顯示，當導入AVM系統於輪圈自動化加工單元後，AVM系統可於線上加工後10秒內預測出輪圈精度項目於平均絕對誤差15%以內，此結果顯示AVM系統確可達到輪圈加工即時且全檢之量測目標。

Wheel machining technology now heads for integration of full automation. Since typical on-line measurement of wheel machining will cause utilization loss, current machining inspection is dominated by off-line measurement methods. This research discusses how to apply the AVM (automatic virtual metrology) system to a WMA (wheel machining automation) system. The required hardware and software of the AVM system are presented and the configurations of the AVM and WMA systems are described in view of architecture. The process of enabling the AVM system to the WMA system is discussed in the aspect of procedure. For comparison, a simulation tool (FlexSim) has been adopted to evaluate the whole performance of applying the AVM system to various WMA systems. A real case study shows that the AVM system can predict accuracy items of a machined wheel within 10 seconds after machining with mean absolute percentage error less than 15%. The result indicates that the AVM system enables the WMA system to achieve the goal of real-time and on-line total inspection.

[1] G. Valiño, C. M. Suárez, J. C. Rico, B. J. Álvarez, and D. Blanco, “Comparison between a Laser Micrometer and a Touch Trigger Probe for Workpiece Measurement on a CNC Lathe,” Advanced Materials Research, vol. Adv. in Materials Processing Tech., pp. 49-54, 2012.
[2] K. S. Svalina and G. Šimunović, “Machined surface quality prediction models based on moving least squares and moving least absolute deviations methods,” Int’l Journal of Advanced Manufacturing Technology, vol. 57, no. 9-12, pp. 1099-1106, 2011.
[3] Wang Yaqing and Qu Weidong, “The Research and Development of On-line Inspection Work-pieces Using CNC Machines,” Advanced Materials Research Vols. 143-144 (2011) pp 244-248, October 2010.
[4] Uk Jung, Myong K. Jeong, and Jye-Chyi Lu, “A Vertical-Energy-Thresholding Procedure for Data Reduction With Multiple Complex Curves,” IEEE Transactions on Systems, Man, And Cybernetics-Part B: Cybernetics, Vol. 36, No. 5, October 2006.
[5] Hongbing Fang, Qian Wang, Yi-Cheng Tu and Mark F. Horstemeyer, “An Efficient Non-dominated Sorting Method for Evolutionary Algorithms,” Evolutionary Computation 16(3): 355-384, September 2008.
[6] K.A. Risbood, U.S. Dixit, “Prediction of surface roughness and dimensional deviation by measuring cutting forces and vibrations in turning process,” Journal of Materials Processing Technology 132 (2003) 203–214, August 2002.
[7] 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 2010 Vol III , July 2010.
[8] Julie Z. Zhang . Joseph C. Chen, “The development of an in-process surface roughness adaptive control system in end milling operations,” Int J Adv Manuf Technol 31:877–887, 2007.
[9] J.V. Abellan-Nebot, R.F. Subirón, “A Review of Machining Monitoring Systems Based on Artificial Intelligence Process Models,” International Journal of Advanced Manufacturing Technology, 47 (2010), pp. 237–257,2010.
[10] 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.
[11] 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.
[12] 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.
[13] 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.