本研究的目的是開發一套對稱高速雙主軸研磨機的監控及異常偵測系統，此對稱高速雙主軸研磨機是用來製造碳化鎢LED探針。首先，狀態監測系統包含三個加速規，一個資料擷取卡以及個人電腦。加速規裝置在研磨機的各個主軸上，藉此收集加工過程中的振動訊號。使用NI LabVIEW開發使用者介面以及一些監測系統的分析演算法。所開發的監測系統應用於研磨過程中已經成功的監測到振動現象，也用於幫助我們進行LED探針研磨的參數的最佳化確認。
一般而言，主軸的性能會隨著使用過程逐漸降低，因為主軸系統中發生摩擦、磨損、疲勞、腐蝕、衝擊和振動，從而到製造加工精度和質量的下降。如果可以早期檢測主軸系統的性能劣化，可以有效的避免嚴重的故障，以及保證工件的精度。考慮到這點，本研究的第二個目的為開發一個異常預兆偵測系統，能夠有效的偵測主軸的異常。預測系統主要由四個部分組成：(1)通過使用熵的演算法抽取振動訊號的特徵；(2)利用正常狀態下的抽取到的特徵建立一個支持向量資料描述(Support Vector data description ,SVDD)模型；(3)訓練好的SVDD模型在以新的資料的特徵進行確認其資料的當前狀態，SVDD的輸出只有1和-1，分別代表著正常狀態與異常狀態；(4)以6個SVDD連續輸出的值的平均作為主軸健康指數。
由於LED探針研磨系統運行到故障的實驗仍在處於籌備的狀態。因此，藉由智能維護系統(Intelligent Maintenance Systems ,IMS)中心所收集到的振動訊號來驗證所提出的預測系統的可行性。實驗結果表明，通過所提出的預測方法可以有效的檢測到軸承磨損所造成的機械異常。

This study aims to develop a monitoring and prognosis system for a symmetric high-speed dual-spindles grinding machine which is used to manufacture Tungsten Carbide LED-probe. Firstly, the condition monitoring system consists of three accelerometers, a data acquisition card and a personal computer. The accelerometers were installed on each spindle of the grinding machine and collected the vibration signals of spindle during the operation. NI Labview software was used to develop the user interface and some analysis algorithms of this monitoring system. The developed monitoring system had been used to detect the resonance phenomenon during grinding process successfully and was also used to help us to determine the optimal process parameters for grinding LED probes.
In general, the performance of the spindle will degrade during use, because the friction, wear, fatigue, corrosion, shock and vibration exist in the spindle systems, which lead to the decrease in machining precision and quality. If the performance degradation of the spindle systems can be detected early, maintenance can be organized effectively to avoid serious failure, and precision of the work-piece can be ensured. In regard to this, the second object of this study is to develop a prognosis system which can detect the abnormality of spindle effectively. The proposed prognosis system consists four major parts: (1) extracting several features of vibration signals by using entropy based algorithms; (2) using the feature data collected from normal operation conditions to train a support vector data description (SVDD) model; (3) the learned SVDD model is used on a new test data with features to determine its current condition, The SVDD output only contain two values, 1 and -1, which stand for normal condition and abnormal condition respectively; (4) The health index of spindle is then defined as the average of 6 consecutive SVDD output.
Because the run-to-fail experiment of the LED-probe grinding system is still under preparation. Therefore, the vibration data collected by Center for Intelligent Maintenance Systems (IMS) were used to evaluate the feasibility of the proposed prognosis system. The experimental results indicate that the abnormality of machine caused by bearing wear can be detected by the proposed prognosis algorithm effectively.

[1]B. Li, M.-Y. Chow, Y. Tipsuwan, and J. C. Hung, Neural-network-based motor rolling bearing fault diagnosis," Industrial Electronics, IEEE Transactions on, vol. 47, pp. 1060-1069, 2000.
[2]B. Samanta, K. R. Al-Balushi, and S. A. Al-Araimi, "Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection," Engineering Applications of Artificial Intelligence, vol. 16, pp. 657-665,Oct-Dec 2003.
[3]N. G. Nikolaou and I. A. Antoniadis, "Rolling element bearing fault diagnosis using wavelet packets," Ndt & E International, vol. 35, pp. 197-205, Apr 2002.
[4]X. R. Zhu, Y. Y. Zhang, and Y. S. Zhu, "Bearing performance degradation assessment based on the rough support vector data description," Mechanical Systems and Signal Processing, vol. 34, pp.
203-217, Jan 2013.
[5]X. S. Lou and K. A. Loparo, "Bearing fault diagnosis based on wavelet transform and fuzzy inference," Mechanical Systems and Signal Processing, vol. 18, pp. 1077-1095, Sep 2004.
[6]S. Abbasion, A. Rafsanjani, A. Farshidianfar, and N. Irani, "Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine," Mechanical Systems and Signal Processing, vol. 21, pp. 2933-2945,Oct 2007.
[7]D. Ho and R. B. Randall, "Optimisation of bearing diagnostic techniques using simulated and actualbearing fault signals," Mechanical Systems and Signal Processing, vol. 14, pp. 763-788, Sep 2000.
[8]F. Y. Cong, J. Chen, and G. M. Dong, "Spectral kurtosis based on AR model for fault diagnosis and condition monitoring of rolling bearing," Journal of Mechanical Science and Technology, vol. 26, pp. 301-306, Feb 2012
[9]R. L. Jiang, J. Chen, G. M. Dong, T. Liu, and W. B. Xiao, "The weak fault diagnosis and condition monitoring of rolling element bearing using minimum entropy deconvolution and envelop spectrum," Proceedings of the Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Science, vol. 227, pp. 1116-1129, 2013.
[10]Y. N. Pen, J. Chen and X. L. Li, "Spectral Entropy: A Complementary Index for Rolling Element Bearing Performance degradation Assessment," Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 223, pp. 1223-1231, 2009.
[11]R. Hao, Z. Peng, Z. Feng and F. Chu, "Application of Support Vector Machine Based on Pattern Spectrum Entropy in Fault Diagnostics of Rolling Element Bearings," Measurement Science and Technology, vol. 22, p. 045708, 2011.
[12]B. Li, P. Zhang, S. Liang and G. Ren, "Feature Extraction and Selection for Fault Diagnosis of Gear Using Wavelet Entropy and Mutual Information," in Signal Processing, 2008. ICSP 2008. 9th
International Conference on, Beijing, China, 2008.
[13]D . Yu, Y. Yang and J. Cheng, "Application of Time Frequency Entropy Method Based on Hilbert-Huang Transform to Gear Fault Diagnosis," Measurement, vol. 40, pp. 823-830, 2007.
[14]M. Costa, A. L. Goldberger, and C. K. Peng, "Multiscale entropy analysis of complex physiologic time series," Physical Review Letters, vol. 89, Aug 5 2002.
[15]S. D. Wu, P. H. Wu, C. W. Wu, J. J. Ding, and C. C. Wang, "Bearing Fault Diagnosis Based on Multiscale Permutation Entropy and Support Vector Machine," Entropy, vol. 14, pp. 1343-1356, Aug 2012.
[16]S. D. Wu, C. W. Wu, T. Y. Wu, and C. C. Wang, "Multi-Scale Analysis Based Ball Bearing Defect Diagnostics Using Mahalanobis Distance and Support Vector Machine," Entropy, vol. 15, pp. 416-433, Feb 2013.
[17]L. Zhang, G. L. Xiong, H. S. Liu, H. J. Zou, and W. Z. Guo, "Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference," Expert Systems with Applications, vol. 37, pp. 6077-6085, Aug 2010.
[18]S. D. Wu, C. W. Wu, S. G. Lin, C. C. Wang, and K. Y. Lee, "Time Series Analysis Using Composite Multiscale Entropy," Entropy, vol. 15, pp. 1069-1084, Mar 2013.
[19]S. D. Wu, C. W. Wu, K. Y. Lee, and S. G. Lin, "Modified multiscale entropy for short-term time series analysis," Physica a-Statistical Mechanics and Its Applications, vol. 392, pp. 5865-5873, Dec 1 2013.
[20]S. D. Wu, P. H. Wu, C. W. Wu, J. J. Ding, and C. C. Wang, "Bearing Fault Diagnosis Based on Multiscale Permutation Entropy and Support Vector Machine," Entropy, vol. 14, pp. 1343-1356, Aug 2012.
[21]B. Samanta, K. R. Al-Balushi, and S. A. Al-Araimi, "Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection," Engineering Applications of Artificial Intelligence, vol. 16, pp. 657-665, Oct-Dec 2003.
[22]S. Abbasion, A. Rafsanjani, A. Farshidianfar, and N. Irani, "Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine," Mechanical Systems and
Signal Processing, vol. 21, pp. 2933-2945, Oct 2007.
[23]S. D. Wu, P. H. Wu, C. W. Wu, J. J. Ding, and C. C. Wang, "Bearing Fault Diagnosis Based on Multiscale Permutation Entropy and Support Vector Machine," Entropy, vol. 14, pp. 1343-1356, Aug 2012.
[24]S. D. Wu, C. W. Wu, T. Y. Wu, and C. C. Wang, "Multi-Scale Analysis Based Ball Bearing Defect Diagnostics Using Mahalanobis Distance and Support Vector Machine," Entropy, vol. 15, pp. 416-433, 2013.
[25]X. R. Zhu, Y. Y. Zhang, and Y. S. Zhu, "Bearing performance degradation assessment based on the rough support vector data description," Mechanical Systems and Signal Processing, vol. 34, pp.
203-217, Jan 2013.
[26]"ISO 10816-1," 1995.
[27]Randall, R. B. and J. Antoni (2011). “Rolling element bearing diagnostics—A tutorial." Mechanical Systems and Signal Processing 25(2): 485-520.
[28]J.W. Cooley and J.W. Tukey, “An Algorithm for the Machine
Calculation of Complex Fourier Series,” Mathematics of Computation, Vol.19, No.90, pp.297-301, 1965.
[29]J. S. Richman and J. R. Moorman, "Physiological time-series analysis using approximate entropy and sample entropy," American Journal of Physiology-Heart and Circulatory Physiology, vol. 278, pp. H2039-H2049, Jun 2000.
[30]R. B. Govindan, J. D. Wilson, H. Eswaran, C. L. Lowery, and H. Preissl, "Revisiting sample entropy analysis," Physica a-Statistical Mechanics and Its Applications, vol. 376, pp. 158-164, Mar 15 2007.
[31]M. Costa, C. K. Peng, A. L. Goldberger, and J. M. Hausdorff, "Multiscale entropy analysis of human gait dynamics," Physica a-Statistical Mechanics and Its Applications, vol. 330, pp. 53-60, Dec 1 2003.
[32]C. Bandt and B. Pompe, "Permutation entropy: A natural complexity measure for time series," Physical Review Letters, vol. 88, Apr 29 2002.
[33]Olofsen, E., J. W. Sleigh, and A. Dahan. "Permutation entropy of the electroencephalogram: a measure of anaesthetic drug effect." British journal of Anaesthesia ,vol. 101,pp. 810-821,2008.
[34]Li, Xiaoli, Suyuan Cui, and Logan J. Voss. "Using permutation entropy to measure the electroencephalographic effects of sevoflurane." Anesthesiology 109, no.3 ,pp. 448-456,2008.
[35]Y. B. Liu, Q. Long, Z. H. Feng and W. L. Liu, "Detection Method for Nonlinear and Nonstationary Signals, "Journal of Vibration and Shock,Dec 2007.
[36]R. Q. Yan, Y. B. Liu and R. X. Gao, "Permutation Entropy: A Nonlinear Statistical Mearsure for Status Characterization of Rotary Machines," Mechanical Systems and Singal Processing,Dec 2011.
[37]Y. C. Zhang, "Complexity and 1/F Noise - a Phase-Space Approach," Journal De Physique I, vol. 1, pp. 971-977, Jul 1991.
[38]Mercer J, " Functions of positive and negative type and their connection with the theory of integral equations. " Philosophical Transactions of the Royal Society, London A 209: 415-446.1909.
[39]V.N. Vapnik ,The Nature of Statistical Learning Theory . New York :Springer-Verlag ,1995.
[40]呂學信, "結合SVDD及SVM分類器於會員人臉確認之研究",私立中原大學機械工程研究所碩士學位論文,2007.
[41]Tax, David MJ, and Robert PW Duin. "Support vector domain description."Pattern recognition letters 20.11 (1999): 1191-1199.
[42]J. Lee, H. Qiu, G. Yu, and J. Lin, "Rexnord Technical Services, Bearing Data Set, IMS, University of Cincinnati. NASA Ames Prognostics Data Repository," ed, 2007.
[43]L. Mi, W. Tan, and R. Chen, "Multi-steps degradation process prediction for bearing based on improved back propagation neural network," Proceedings of the Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Science, vol. 227, pp. 1544-1553, Jul 2013.
[44]D. Fernandez-Francos, D. Martinez-Rego, O. Fontenla-Romero, and A. Alonso-Betanzos, "Automatic bearing fault diagnosis based on one-class v-SVM," Computers & Industrial Engineering, vol. 64, pp. 357-365, Jan 2013.