感應馬達被廣泛應用在工業中，例如：抽水幫浦、空壓機及風扇等。機械在長時間運轉下容易受到機械初期損壞致使疲勞破壞，嚴重可能導致停機。許多的機械故障診斷技術早已發展數十年，常見的診斷方式包含機械振動及馬達電流分析，這些分析方法各有適合應用的地方及不同優缺點。
在先前的資料融合(Data Fusion)文獻中，並沒有針對振動及電流訊號作詳細的特徵擷取探討，本論文將針對振動訊號及電流訊號作有系統的分析，並提出一套擷取特徵的方法。這些訊號由於外部噪音、低訊噪比及時變訊號，機械初期損壞非常難偵測，利用傳統時域及頻域分析方式不易辨識，則本篇論文將利用小波包分解(Wavelet Packet Decomposition, WPD)分別擷取機械振動及馬達電流時頻域特徵，並利用支持向量機(Support Vector Machine, SVM)做為分類器。藉由特徵級(Feature-level)及決策級(Decision-level)兩種資料融合方法，將機械振動及馬達電流資料整合決策。

Induction machines have been widely used in the industry today, such as water pumps, air compressors, and fans. They are prone to fatigue failures after long operating hours, resulting in catastrophic breakdown. These failures are preceded by incipient faults under which the machines continue to function, but with low efficiency. Numerous fault detection and isolation techniques for the diagnosis of induction machines have been proposed over the past few decades. Among these techniques, the motor current signature analysis (MCSA) and the vibration analyses are two of the most common signal-based condition monitoring methods. They are often adopted independently but each method has its strengths and weaknesses. The incipient faults, however, are difficult to identify because of their low signal-to-noise ratio, vulnerability to external disturbances, and non-stationarity.
Previous literatures did not consider the integration of the vibration and current signals of the induction motor, and they did not propose the feature extraction of the vibration and current signals in detail either. This research developed the systematic signal preprocessing and feature extraction methodologies. It applied the wavelet packet decomposition (WPD) to extract the time-frequency features of the current and vibration measurements respectively, and used the support vector machines (SVM) as classifiers for the decision making. Two data fusion schemes, feature-level fusion and decision-level fusion, are proposed. By using data fusion theory, the current and vibration information could be integrated to improve the accuracy of the diagnosis.

[1] R. K. Mobley, An introduction to predictive maintenance. Butterworth-Heinemann, 2002.
[2] J. Lee et al., "Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications," Mechanical systems and signal processing, vol. 42, no. 1-2, pp. 314-334, 2014.
[3] R. K. Mobley, Vibration fundamentals. Butterworth-Heinemann, 1999.
[4] S. J. Lacey, "An overview of bearing vibration analysis," Maintenance & asset management, vol. 23, no. 6, pp. 32-42, 2008.
[5] S. Jeevanand and A.T. Mathew, "Condition monitoring of induction motors using wavelet based analysis of vibration signals," IEEE Second International Conference on Future Generation Communication and Networking Symposia, 2008. FGCNS'08, Vol. 3, 2008.
[6] B. P. Graney and K. Starry, "Rolling element bearing analysis," Materials Evaluation, vol. 70, no. 1, 2012.
[7] Q. Hu et al., "Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble," Mechanical Systems and Signal Processing, vol. 21, no. 2, pp. 688-705, 2007.
[8] D. Wang et al., "Rolling element bearing fault detection using an improved combination of Hilbert and wavelet transforms," Journal of Mechanical Science and Technology, vol. 23, no. 12, pp. 3292-3301, 2009.
[9] Z. Wei et al., "Incipient fault diagnosis of rolling element bearing based on wavelet packet transform and energy operator," WSEAS TRANSACTIONS on SYSTEMS, vol. 10, no. 3, pp. 81-90, 2011. 
[10] P. G. Kulkarni and A. D. Sahasrabudhe, "Application Of Wavelet Transform For Fault Diagnosis of Rolling Element Bearings," International Journal of Technology Enhancements and Emerging Engineering Research, vol. 2, no. 4, pp. 138-148, 2013.
[11] J. Ma et al., "A fault detection method of rolling bearing based on wavelet packet-cepstrum," Res. J. Appl. Sci. Eng. Technol., vol. 5, no. 12, pp. 3402-3406, 2013.
[12] M. Wenxing and L. Meng, "Fault pattern recognition of rolling bearings based on wavelet packet and support vector machine," IEEE 27th Chinese Control Conference, 2008. CCC'08, 2008
[13] S. Fang and W. Zijie, "Rolling bearing fault diagnosis based on wavelet packet and RBF neural network." IEEE Chinese Control Conference, 2007. CCC'07, 2007.
[14] J. Chebil et al, "Wavelet decomposition for the detection and diagnosis of faults in rolling element bearings," Jordan Journal of Mechanical and Industrial Engineering, vol. 3, no. 4, pp. 260-267, 2009.
[15] S. Abbasion et al., "Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine," Mechanical Systems and Signal Processing, vol. 21, no. 7, pp. 2933-2945, 2007.
[16] P. Konar and P. Chattopadhyay, "Bearing fault detection of induction motor using wavelet and Support Vector Machines (SVMs)," Applied Soft Computing, vol. 11, no. 6, pp. 4203-4211, 2011.
[17] A. Khezzar et al., "Induction motor diagnosis using line neutral voltage signatures." IEEE Transactions on Industrial Electronics, vol. 56, no. 11, pp. 4581-4591, 2009.
[18] H. Çalış, and A. Çakır, "Experimental study for sensorless broken bar detection in induction motors," Energy Conversion and Management, vol. 49, no. 4, pp. 854-862, 2008.
[19] H. Çalış and A. Çakır, "Rotor bar fault diagnosis in three phase induction motors by monitoring fluctuations of motor current zero crossing instants," Electric Power Systems Research, vol. 77, no. 5-6, pp. 385-392, 2007.
[20] W. T. Thomson and R. J. Gilmore, "Motor Current Signature Analysis To Detect Faults In Induction Motor Drives-Fundamentals, Data Interpretation, And Industrial Case Histories," Proceedings of the 32nd Turbomachinery Symposium. Texas A&M University. Turbomachinery Laboratories, 2003.
[21] E. L. Bonaldi et al., Predictive maintenance by electrical signature analysis to induction motors. Induction Motors-Modelling and Control. InTech, 2012, ch. 20.
[22] D. Miljković, "Brief review of motor current signature analysis," HDKBR INFO Magazin, vol. 5, no. 1, pp. 14-26, 2015.
[23] C. Kar and A. R. Mohanty, "Monitoring gear vibrations through motor current signature analysis and wavelet transform," Mechanical systems and signal processing, vol. 20, no. 1, pp. 158-187, 2006.
[24] Z. Ye et al., "Current signature analysis of induction motor mechanical faults by wavelet packet decomposition," IEEE transactions on industrial electronics, vol. 50, no. 6, pp. 1217-1228, 2003.
[25] J. CusidÓCusido et al., "Fault detection in induction machines using power spectral density in wavelet decomposition," IEEE Transactions on Industrial Electronics, vol. 55, no. 2, pp. 633-643, 2008.
[26] A. Bouzida et al., "Fault diagnosis in industrial induction machines through discrete wavelet transform," IEEE Transactions on Industrial Electronics, vol. 58, no. 9, pp. 4385-4395, 2011.
[27] A. Widodo and B. S. Yang, "Wavelet support vector machine for induction machine fault diagnosis based on transient current signal," Expert Systems with Applications, vol. 35, no. 1-2, pp. 307-316, 2008.
[28] H. Keskes et al., "Broken rotor bar diagnosis in induction machines through stationary wavelet packet transform and multiclass wavelet SVM," Electric Power Systems Research, vol. 97, pp. 151-157, 2013.
[29] S. E. Pandarakone et al., "Distinct fault analysis of induction motor bearing using frequency spectrum determination and support vector machine," IEEE Transactions on Industry Applications, vol. 53, no. 3, pp. 3049-3056, 2017.
[30] E. Artigao et al., "Current signature and vibration analyses to diagnose an in-service wind turbine drive train," Energies, vol. 11, no. 4, pp. 1-18, 2018.
[31] Z. Hu et al., "Fusion of multi-class support vector machines for fault diagnosis," IEEE American Control Conference, 2005. Proceedings of the 2005, 2005.
[32] G. Niu et al., "Decision-level fusion based on wavelet decomposition for induction motor fault diagnosis using transient current signal," Expert Systems with Applications, vol. 35, no. 3, pp. 918-928, 2008.
[33] M. S. Safizadeh and S. K. Latifi, "Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell," Information Fusion, vol. 18, pp. 1-8, 2014.
[34] L. L. Jiang et al., "Fault diagnosis of rotating machinery based on multi-sensor information fusion using SVM and time-domain features," Shock and Vibration, vol. 2014, 2014.
[35] X. Liu et al., "Machinery fault diagnosis based on fuzzy measure and fuzzy integral data fusion techniques," Mechanical Systems and Signal Processing, vol. 23, no. 3, pp. 690-700, 2009.
[36] J. D. Wu and C. H. Liu, "An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network," Expert systems with applications, vol. 36, no. 3, pp. 4278-4286, 2009. 
[37] A. Tabrizi et al., "Early damage detection of roller bearings using wavelet packet decomposition, ensemble empirical mode decomposition and support vector machine," Meccanica, vol. 50, no. 3, pp. 865-874, 2015.
[38] S. Abbasion et al., "Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine," Mechanical Systems and Signal Processing, vol. 21, no. 7, pp. 2933-2945, 2007.
[39] J. M. Keller and J. Osborn, "Training the fuzzy integral," International Journal of Approximate Reasoning, vol. 15, no. 1, pp. 1-24 1996.
[40] M. Sugeno, "Theory of fuzzy integrals and its applications," Doctoral Thesis, Tokyo Institute of Technology, 1974.