本論文主要討論工具機使用安川（YASKAWA）驅動器本身之速度前饋情況下，驅動器參數中位置迴路增益K_p、速度迴路響應頻寬P_n、速度迴路積分時間常數T_i、前饋比例V_ff與前饋濾波器的時間常數τ之系統參數對精度最佳化關係，並利用基因演算法（Genetic Algorithm, GA）鑑別出最佳化參數。再依驅動器的特性，建立一個最佳化參數關係表，以此應用於實際工具機之加工上，藉此減少參數調整時間。
另外提出一個Space Filter空間濾波器用於路徑平滑化，改善相鄰相似軌跡不平滑，導致速度規劃不一致之類似造成工件產生刀痕之現象。並引入逆向工程學裡，網格平滑化的理論，用於改進此濾波器平滑化的方法之中，最後比較方法改進前後對路徑平滑效果的影響。

In this paper, we focus on optimizing the machining precision of computer numerically controlled milling machines using Yasukawa servo drive with speed loop feedforward. For the sake of finding the optimized machining accuracy, we use the genetic algorithm to adjust the drive’s parameters, including the position loop gain, speed loop gain, speed loop integral time constant, feedforward ratio and feedforward filter time constant. Due to the characteristics of the drive, we build an optimum parameter table that can enhance the efficiency of processing and reduce much of the time for setting parameters.
In addition, we also present a Space Filter for smoothing tool paths and decreasing cutting streaks on a workpiece. According to the mesh smoothing theory of reverse engineering, we design a smoothing method of the filter, and in the end we use Rev CAD, a software developed for reverse engineering, to help comparing the effect of our smoothing method with that of the conventional approach.

[1] Veronesi. M, Visioli. A, “Automatic feedforward tuning for PID control loops,” European. Control Conference, pp.3919-3924, 2013.
[2] Liangliang. Yang, Weimin. Shi, Laihu. Peng, “Research on Feedforward Parameter Optimization of Linear Servo System Based on Iterative Learning of Orthogonal Projection,” 2nd International Conference on. Information Science and Control Engineering (ICISCE), pp.889-892, 2015.
[3] Sugimoto. K, Ito. F, Mateo. L.A,, “Feedforward control with on-line tuning: A perspective on two-degree-of-freedom structure,” International Conference on. Advanced Mechatronic Systems (ICAMechS), pp.55-60, 2014.
[4] K. S. Narendra, Y. H. Lin, L. S. Valavani, “Stable adaptive controller design, part II: proof of stability,” IEEE Transactions on Automatic Control, vol. 25, no. 3, pp. 440-448, 1980.
[5] F. J. Lin, R. J. Wai, K. K. Shyu, T. M. Liu, “Recurrent fuzzy neural network control for piezoelectric ceramic linear ultrasonic motor drive,＂ IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control, vol. 48, no. 4, pp. 900-913, 2001.
[6] F. J. Lin, C. C. Lee, “Adaptive backstepping control for linear induction motor drive to track periodic references,＂IEE Transactions on Electric Power Applications, vol. 147, no. 6, Nov., pp. 449-458, 2000.
[7] R. J. Wai, F. J. Lin, R. Y. Duan, K. Y. Hsieh, J. D. Lee, “Robust fuzzy neural network control for linear ceramic motor drive via backstepping design technique,＂IEEE Transactions on Fuzzy Systems, vol. 10, no. 1, pp. 102-112, 2002.
[8] F. J. Lin, C. H. Lin, “On-line gain tuning using RFNN for linear synchronous motor,＂ in Proc. IEEE PESC-2001, pp. 766-771, June. 2001.
[9] X. Li, B. Yao, “Adaptive robust precision motion control of linear motors with negligible electrical dynamics: theory and experiments,” IEEE Transactions on Mechatronics, vol. 6, no. 4, pp. 444-452, 2001.
[10] 賴景義、翁文德，逆向工程理論與應用，圖書股份有限公司，台北市，民國九十三年
[11] Agarwal. S, Aggarwal. A, “Model driven reverse engineering of user interface — A comparative study of static and dynamic model generation tools,” International Conference on. Parallel, Distributed and Grid Computing, pp.268–273, 2014.
[12] Smith. J, “Non-destructive state machine reverse engineering,” 6th International Symposium Conference on. Resilient Control Systems (ISRCS), pp.120–124, 2013.
[13] Stamm. M.C, Liu. K.J.R, “Protection against reverse engineering in digital cameras,” IEEE International Conference on. Acoustics, Speech and Signal Processing (ICASSP), pp.8702-8706, 2013.
[14] Burston. M, Sabatini. R, Gardi. A, Clothier. R, “Reverse engineering of a fixed wing Unmanned Aircraft 6-DoF model based on laser scanner measurements,” IEEE. Metrology for Aerospace (MetroAeroSpace), pp.144–149, 2014.
[15] Aho. P, Raty. T, Menz. N, “Dynamic reverse engineering of GUI models for testing,” International Conference on. Control, Decision and Information Technologies (CoDIT), pp.441–447, 2013.
[16] 王進德，類神經網路與模糊控制理論入門與應用，全華圖書股份有限公司，台北市，民國九十五年