人工神經網路已經被廣泛的應用於馬達診斷的領域中，本文運用深度學習架構的1D-捲積神經網路來提取特徵並作特徵分類來達成診斷。
本論文主旨在於使用一套診斷系統來辨識出三相感應電機轉子斷條故障。利用加速規取得震動訊號後，經由快速傅立葉轉換將時域訊號轉換為頻域訊號。獲得之訊號經過主成份分析法做適當的維度選擇，最後基於1D-捲積神經網路進行分析分類。本實驗擷取四種不同轉子斷條狀態下的震動訊號，所有資料被分為兩組用來訓練及測試1D-捲積神經網路機制，轉子情況包含無缺陷及三種故障狀態。本實驗使用一15千瓦三相感應馬達為實驗項目，實驗結果證明本方法可以有效的診斷馬達的四種不同轉子斷條狀態，其中第一部分實驗結果得到最佳辨識率與最小誤差率分別為99.30%及3.54%，且預測模型也有高達分別為99%和98%的精密度和召回率，而第二部分實驗結果得到最佳辨識率與最小誤差率分別為99.30%及2.84%，且預測模型也有高達99%的召回率。

Artificial neural networks have been widely used in the field of motor diagnosis. This study uses the 1D-convolution neural network of deep learning architecture to extract and classify features to achieve diagnosis.In this thesis, a fault diagnosis system is proposed to perform rotor bar fault detection in three-phase induction motors. Vibration signal is acquired by accelerometers and the signal is transformed from time domain to frequency domain via Fast Fourier Transform (FFT). The transformed signals are processed by Principal Component Analysis(PCA), and based on 1D-convolution neural network for analysis and classification. The rotor condition includes no defects and three fault conditions in this study. All data is divided into two groups for training and testing 1D-convolution neural networks. This study uses a 15 kW three-phase induction motor as a test case. The first part of the experimental results , that the best recognition rate and loss rate are 99.30% and 3.69%, and the model has high precision and recall which about 99% and 98%. The second part of the experimental results using oversampling, that the recognition rate and loss rate can achieve 99.30% and 2.84%, and the model has high recall value about 99% .

[1]P. Albrecht, J. Appiarius, R. McCoy, E. Owen, and D. Sharma, "Assessment of the reliability of motors in utility applications-Updated," IEEE Transactions on Energy conversion, pp. 39-46, 1986.
[2]A. H. Bonnett and G. C. Soukup, "Cause and analysis of stator and rotor failures in three-phase squirrel-cage induction motors," IEEE Transactions on Industry applications, vol. 28, pp. 921-937, 1992.
[3]M. Liggins II, D. Hall, and J. Llinas, Handbook of multisensor data fusion: theory and practice: CRC press, 2017.
[4]K. S. Gaeid, H. W. Ping, M. Khalid, and A. L. Salih, "Fault diagnosis of induction motor using MCSA and FFT," Electrical and Electronic Engineering, vol. 1, pp. 85-92, 2011.
[5]M. Nemec, K. Drobnic, D. Nedeljkovic, R. Fiser, and V. Ambrozic, "Detection of broken bars in induction motor through the analysis of supply voltage modulation," IEEE transactions on industrial electronics, vol. 57, pp. 2879-2888, 2010.
[6]A. Singh, B. Grant, R. DeFour, C. Sharma, and S. Bahadoorsingh, "A review of induction motor fault modeling," Electric Power Systems Research, vol. 133, pp. 191-197, 2016.
[7]I. Kathir, S. Balakrishnan, and R. Bevila, "Fault analysis of induction motor," in Emerging Trends in Electrical and Computer Technology (ICETECT), 2011 International Conference on, pp. 476-479, 2011.
[8]I. Kathir, S. Balakrishnan, and G. Sakthivel, "Detection of rotor fault in an induction motor under standstill condition," in Advances in Engineering, Science and Management (ICAESM), 2012 International Conference on, pp. 547-552, 2012.
[9]M. Sin, W. Soong, and N. Ertugrul, "Induction machine on-line condition monitoring and fault diagnosis-A survey," in Australasian universities power engineering conference, pp. 1-6, 2003.
[10] Y. Han and Y. Song, "Condition monitoring techniques for electrical equipment-a literature survey," IEEE Transactions on Power delivery, vol. 18, pp. 4-13, 2003.
[11]P. N. Chen, "使用K-鄰近演算法之三相感應馬達轉子故障診斷系統," 成功大學電機工程學系學位論文, pp.1-58, 2015.
[12]K. V. Kumar, "A review of voltage and current signature diagnosis in industrial drives," International Journal of Power Electronics and Drive Systems (IJPEDS), vol. 1, pp. 75-82, 2011.
[13]P. Pillay and Z. Xu, "Motor current signature analysis," in Industry Applications Conference, 1996. Thirty-First IAS Annual Meeting, IAS'96., Conference Record of the 1996 IEEE, pp. 587-594, 1996.
[14]A. Gheitasi, "Motors fault recognition using distributed current signature analysis," Auckland University of Technology, 2012.
[15]E. L. Bonaldi, L. E. d. L. de Oliveira, J. G. B. da Silva, G. Lambert-Torresm, and L. E. B. da Silva, "Predictive maintenance by electrical signature analysis to induction motors," in Induction Motors-Modelling and Control, ed: InTech, 2012.
[16]A. Korde, "On-Line Condition Monitoring of Motors Using Electrical Signature Analyisis," Recent Advances in Condition Based Plant Maintenance, 17-18 May 2002, Mumbay
[17]D. Miljković, "Review of machine condition monitoring based on vibration data," in MIPRO 2008, 2008.
[18]S. Lawrence, C. L. Giles, A. C. Tsoi, and A. D. Back, "Face recognition: A convolutional neural-network approach," IEEE transactions on neural networks, vol. 8, pp. 98-113, 1997.
[19]P. Y. Simard, D. Steinkraus, and J. C. Platt, "Best practices for convolutional neural networks applied to visual document analysis," in null, p. 958, 2003.
[20]P. H. Pinheiro and R. Collobert, "Recurrent convolutional neural networks for scene labeling," in 31st International Conference on Machine Learning (ICML), 2014.
[21]J. W. Cooley, "The re-discovery of the fast Fourier transform algorithm," Microchimica Acta, vol. 93, pp. 33-45, 1987.
[22]C. Rader and N. Brenner, "A new principle for fast Fourier transformation," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 24, pp. 264-266, 1976.
[23]S. Winograd, "On the multiplicative complexity of the discrete Fourier transform," Advances in Mathematics, vol. 32, pp. 83-117, 1979.
[24]J. W. Cooley and J. W. Tukey, "An algorithm for the machine calculation of complex Fourier series," Mathematics of computation, vol. 19, pp. 297-301, 1965.
[25]C. H. Papadimitriou, "Optimality of the fast Fourier transform," Journal of the ACM (JACM), vol. 26, pp. 95-102, 1979.
[26]Y. T. Lai and C. Y. Hsu , "Design of 2048-point Real-Time FFT of OFDM by Using Reconfigurable FPGA", Department of Electrical Engineering National Cheng Kung University ,Thesis for Master of Scince June,2004.
[27]F. J. Harris, "On the use of windows for harmonic analysis with the discrete Fourier transform," Proceedings of the IEEE, vol. 66, pp. 51-83, 1978.
[28]D. P. Mitchell and A. N. Netravali, "Reconstruction filters in computer-graphics," ACM Siggraph Computer Graphics, vol. 22, pp. 221-228, 1988.
[29]R. Sullivan, A. Timmermann, and H. White, "Data‐snooping, technical trading rule performance, and the bootstrap," The journal of Finance, vol. 54, pp. 1647-1691, 1999.
[30]D. C. Rife and G. Vincent, "Use of the discrete Fourier transform in the measurement of frequencies and levels of tones," Bell System Technical Journal, vol. 49, pp. 197-228, 1970.
[31]K. Pearson, "LIII. On lines and planes of closest fit to systems of points in space," The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, vol. 2, pp. 559-572, 1901.
[32]M. K. Warmuth and D. Kuzmin, "Randomized online PCA algorithms with regret bounds that are logarithmic in the dimension," Journal of Machine Learning Research, vol. 9, pp. 2287-2320, 2008.
[33]A. N. Gorban, B. Kégl, D. C. Wunsch, and A. Y. Zinovyev, Principal manifolds for data visualization and dimension reduction vol. 58: Springer, 2008.
[34]C. Linlin, L. Haitao, and H. Yanshun, "Application of convolutionalnneural networks inclassification of high resolution remote sensing imagery," Science of Surveying and Mapping, vol. 41, pp. 170-175, 2016.
[35]Y. Chunjing, Z. Yueyao, Z. Yaxuan, and H. Liu, "Application of convolutional neural network in classfication of high resolution agricultural remoye sensing images," International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, vol. 42, 2017.
[36]F. Aminzadeh and P. deGroot, "A neural networks based seismic object detection technique," in SEG Technical Program Expanded Abstracts 2005, ed: Society of Exploration Geophysicists, pp. 775-778, 2005.
[37]M. D. Zeiler and R. Fergus, "Stochastic pooling for regularization of deep convolutional neural networks," arXiv preprint arXiv:1301.3557, 2013.
[38]A. Deshpande, "The 9 Deep Learning Papers You Need To Know About (Understanding CNNs Part 3)," University of California, Los Angeles (UCLA), 2016.
[39]D. Scherer, A. Müller, and S. Behnke, "Evaluation of pooling operations in convolutional architectures for object recognition," in Artificial Neural Networks–ICANN 2010, ed: Springer, pp. 92-101, 2010.
[40]Y. P. Cheng, "基於倒傳遞類神經法之三相感應馬達故障診斷系統," 成功大學電機工程學系學位論文, pp. 1-50, 2018.
[41]J. M. Syu, "支持向量機之三相感應馬達軸承故障診斷系統," 成功大學電機工程學系學位論文, pp. 1-63, 2015.