隨著科技的不斷進步，現代工業中感應馬達的故障診斷取得了重要的成就。傳統的馬達故障診斷方法量測電壓、電流和振動訊號進行訊號式異常診斷，或是建立感應馬達數學模型進行模型式異常診斷，並使用機器學習進行故障分類。然而，傳統的手動特徵提取方法，在處理大數據時效率低下且準確率不穩定。為了克服這些問題，本研究採用了深度學習的方法，結合卷積神經網路和遞迴神經網路的變體架構，進行基於電流殘差的感應馬達故障診斷。
本研究通過實際量測感應馬達的運行狀況，利用三相電壓和電流建立感應馬達模型。透過將實際電流與模型輸出電流的差值訊號進行分析，能夠更準確地檢測出馬達的異常情況。實驗結果顯示，相較於原始電流訊號，殘差訊號更具有檢測故障特徵的敏感性。深度學習架構在故障診斷方面展現了優勢，不論是本文提出的一維卷積神經網路結合遞迴神經網路的變體架構，或是兩者神經網路分別單獨使用的架構，其分類率皆優於傳統的機器學習方法如支持向量機。此外，本研究還應用轉移學習的方法，在不同閥門開度的情況下進行故障分類，並獲得了快速且有效的結果。

With the continuous advancement of technology, fault diagnosis of induction motors in modern industries has achieved significant progress. Traditional motor fault diagnosis methods rely on signal-based anomaly diagnosis, which involves measuring voltage, current, and vibration signals, or model-based anomaly diagnosis by establishing mathematical models of induction motors, using machine learning for fault classification. However, traditional manual feature extraction methods are inefficient and have unstable accuracy when dealing with big data. To overcome these challenges, this study adopts deep learning techniques, combining convolutional neural networks (CNNs) and Gated Recurrent Unit (GRU), for induction motor fault diagnosis based on current residuals.
By measuring the operational conditions of induction motors, a motor model is built using the voltage and current signals. Analyzing the difference between the measured current and the model's output current, the residual signal can accurately detect motor abnormalities. Experimental results demonstrate that the residual signal is more sensitive in detecting fault features compared to the original current signal. The deep learning architectures, whether the proposed 1D CNN combined with GRU or individually used CNN and GRU, outperform traditional machine learning methods such as support vector machines (SVM) in terms of classification accuracy. Furthermore, transfer learning is applied to achieve fast and effective fault classification under different valve opening conditions.

[1] C. De Angelo, G. Bossio, S. Giaccone, G. O. Garcia, J. Solsona, and M. I. Valla, "Model based stator fault detection in induction motors," in IECON 2006-32nd Annual Conference on IEEE Industrial Electronics, 2006: IEEE, pp. 1095-1100.
[2] S. Duvvuri and K. Detroja, "Model-based broken rotor bars fault detection and diagnosis in squirrel-cage induction motors," in 2016 3rd conference on control and fault-tolerant systems (SysTol), 2016: IEEE, pp. 537-539.
[3] K. M. Siddiqui, K. Sahay, and V. Giri, "Health monitoring and fault diagnosis in induction motor-a review," International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, vol. 3, no. 1, pp. 6549-6565, 2014.
[4] D. Lopez-Perez and J. Antonino-Daviu, "Application of infrared thermography to failure detection in industrial induction motors: case stories," IEEE Transactions on Industry Applications, vol. 53, no. 3, pp. 1901-1908, 2017.
[5] W. Purbowaskito, "Data-driven Model-based Fault Diagnosis for the Predictive Maintenance of Induction Motors," 2022.
[6] W. Dehina, M. Boumehraz, F. Kratz, and J. Fantini, "Diagnosis and comparison between stator current analysis and vibration analysis of static eccentricity faults in the induction motor," in 2019 4th International Conference on Power Electronics and their Applications (ICPEA), 2019: IEEE, pp. 1-4.
[7] N. Mehla and R. Dahiya, "An approach of condition monitoring of induction motor using MCSA," International journal of systems applications, Engineering and development, vol. 1, no. 1, pp. 13-17, 2007.
[8] 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, no. 2, pp. 85-92, 2011.
[9] N. Mehala and R. Dahiya, "Motor current signature analysis and its applications in induction motor fault diagnosis," International journal of systems applications, engineering & development, vol. 2, no. 1, pp. 29-35, 2007.
[10] W. T. Thomson and M. Fenger, "Current signature analysis to detect induction motor faults," IEEE Industry Applications Magazine, vol. 7, no. 4, pp. 26-34, 2001.
[11] L. Eren and M. J. Devaney, "Bearing damage detection via wavelet packet decomposition of the stator current," IEEE Transactions on Instrumentation and measurement, vol. 53, no. 2, pp. 431-436, 2004.
[12] M. Aerhpanahi, S. Sadeghi, and H. A. Roknabadi, "Broken rotor bar detection in induction motor via stator current derivative," in 2004 IEEE International Conference on Industrial Technology, 2004. IEEE ICIT'04., 2004, vol. 3: IEEE, pp. 1363-1367.
[13] Z. Ye, B. Wu, and A. Sadeghian, "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.
[14] 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: IntechOpen, 2012.
[15] A. P. Parra, M. C. A. Enciso, J. O. Ochoa, and J. A. P. Peñaranda, "Stator fault diagnosis on squirrel cage induction motors by ESA and EPVA," in 2013 Workshop on Power Electronics and Power Quality Applications (PEPQA), 2013: IEEE, pp. 1-6.
[16] R. V. Beard, "Failure accomodation in linear systems through self-reorganization," Massachusetts Institute of Technology, 1971.
[17] J. Chen and R. J. Patton, Robust model-based fault diagnosis for dynamic systems. Springer Science & Business Media, 2012.
[18] S. X. Ding, Model-based fault diagnosis techniques: design schemes, algorithms, and tools. Springer Science & Business Media, 2008.
[19] G. H. B. Foo, X. Zhang, and D. M. Vilathgamuwa, "A sensor fault detection and isolation method in interior permanent-magnet synchronous motor drives based on an extended Kalman filter," IEEE Transactions on Industrial Electronics, vol. 60, no. 8, pp. 3485-3495, 2013.
[20] B.-G. Park, R.-Y. Kim, and D.-S. Hyun, "Fault diagnosis using recursive least square algorithm for permanent magnet synchronous motor drives," in 8th International Conference on Power Electronics-ECCE Asia, 2011: IEEE, pp. 2506-2510.
[21] M. Heydarzadeh, M. Zafarani, E. Ugur, B. Akin, and M. Nourani, "A model-based signal processing method for fault diagnosis in PMSM machine," in 2017 IEEE Energy Conversion Congress and Exposition (ECCE), 2017: IEEE, pp. 3160-3164.
[22] K. Kim and A. G. Parlos, "Induction motor fault diagnosis based on neuropredictors and wavelet signal processing," IEEE/ASME Transactions on mechatronics, vol. 7, no. 2, pp. 201-219, 2002.
[23] X.-h. Wang and Y.-G. He, "Fuzzy model based on-line stator winding turn fault detection for induction motors," in Sixth International Conference on Intelligent Systems Design and Applications, 2006, vol. 1: IEEE, pp. 838-843.
[24] T. Ahmad and M. N. Aziz, "Data preprocessing and feature selection for machine learning intrusion detection systems," ICIC Express Lett, vol. 13, no. 2, pp. 93-101, 2019.
[25] V. Bolón-Canedo, N. Sánchez-Maroño, and A. Alonso-Betanzos, "A review of feature selection methods on synthetic data," Knowledge and information systems, vol. 34, pp. 483-519, 2013.
[26] Y. Saeys, I. Inza, and P. Larranaga, "A review of feature selection techniques in bioinformatics," bioinformatics, vol. 23, no. 19, pp. 2507-2517, 2007.
[27] B. Mahesh, "Machine learning algorithms-a review," International Journal of Science and Research (IJSR).[Internet], vol. 9, no. 1, pp. 381-386, 2020.
[28] K. K. Hyde et al., "Applications of supervised machine learning in autism spectrum disorder research: a review," Review Journal of Autism and Developmental Disorders, vol. 6, pp. 128-146, 2019.
[29] S. Yadav and S. Shukla, "Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification," in 2016 IEEE 6th International conference on advanced computing (IACC), 2016: IEEE, pp. 78-83.
[30] 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.
[31] N.-T. Nguyen, J.-M. Kwon, and H.-H. Lee, "Fault diagnosis of induction motor using decision tree with an optimal feature selection," in 2007 7th Internatonal Conference on Power Electronics, 2007: IEEE, pp. 729-732.
[32] R. K. Patel and V. Giri, "Feature selection and classification of mechanical fault of an induction motor using random forest classifier," Perspectives in Science, vol. 8, pp. 334-337, 2016.
[33] S. Kiranyaz, T. Ince, O. Abdeljaber, O. Avci, and M. Gabbouj, "1-D convolutional neural networks for signal processing applications," in ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019: IEEE, pp. 8360-8364.
[34] W. Jiang, C. Wang, J. Zou, and S. Zhang, "Application of deep learning in fault diagnosis of rotating machinery," Processes, vol. 9, no. 6, p. 919, 2021.
[35] X. Guo, L. Chen, and C. Shen, "Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis," Measurement, vol. 93, pp. 490-502, 2016.
[36] O. Janssens et al., "Convolutional neural network based fault detection for rotating machinery," Journal of Sound and Vibration, vol. 377, pp. 331-345, 2016.
[37] D.-T. Hoang and H.-J. Kang, "Convolutional neural network based bearing fault diagnosis," in Intelligent Computing Theories and Application: 13th International Conference, ICIC 2017, Liverpool, UK, August 7-10, 2017, Proceedings, Part II 13, 2017: Springer, pp. 105-111.
[38] M.-Q. Tran, M.-K. Liu, Q.-V. Tran, and T.-K. Nguyen, "Effective fault diagnosis based on wavelet and convolutional attention neural network for induction motors," IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-13, 2021.
[39] S. Misra et al., "Fault detection in induction motor using time domain and spectral imaging-based transfer learning approach on vibration data," Sensors, vol. 22, no. 21, p. 8210, 2022.
[40] D. Xiao, Y. Huang, X. Zhang, H. Shi, C. Liu, and Y. Li, "Fault diagnosis of asynchronous motors based on LSTM neural network," in 2018 prognostics and system health management conference (PHM-Chongqing), 2018: IEEE, pp. 540-545.
[41] J. Wang, P. Fu, L. Zhang, R. X. Gao, and R. Zhao, "Multilevel information fusion for induction motor fault diagnosis," IEEE/ASME Transactions on Mechatronics, vol. 24, no. 5, pp. 2139-2150, 2019.
[42] J. Wang, P. Fu, S. Ji, Y. Li, and R. X. Gao, "A light weight multisensory fusion model for induction motor fault diagnosis," IEEE/ASME Transactions on Mechatronics, vol. 27, no. 6, pp. 4932-4941, 2022.
[43] C. Li, S. Zhang, Y. Qin, and E. Estupinan, "A systematic review of deep transfer learning for machinery fault diagnosis," Neurocomputing, vol. 407, pp. 121-135, 2020.
[44] S. Shao, S. McAleer, R. Yan, and P. Baldi, "Highly accurate machine fault diagnosis using deep transfer learning," IEEE Transactions on Industrial Informatics, vol. 15, no. 4, pp. 2446-2455, 2018.
[45] C. Sun, M. Ma, Z. Zhao, S. Tian, R. Yan, and X. Chen, "Deep transfer learning based on sparse autoencoder for remaining useful life prediction of tool in manufacturing," IEEE transactions on industrial informatics, vol. 15, no. 4, pp. 2416-2425, 2018.
[46] M. J. Hasan and J.-M. Kim, "Bearing fault diagnosis under variable rotational speeds using stockwell transform-based vibration imaging and transfer learning," Applied Sciences, vol. 8, no. 12, p. 2357, 2018.
[47] A. Makur and S. K. Mitra, "Warped discrete-Fourier transform: Theory and applications," IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, vol. 48, no. 9, pp. 1086-1093, 2001.
[48] Y. James, "[Data Analysis & Machine Learning] Lecture 5.1: Introduction to Convolutional Neural Networks (Convolutional Neural Network)."
[49] A. M. Sefidian, "Understanding 1D, 2D, and 3D convolutional layers in deep neural networks."
[50] Ray, "Difference between 1D convolution, 2D convolution, 3D convolution? ?."
[51] L. F. Office, "Machine Learning Notebook: Recurrent Neural Networks (RNN) Reading Summary."
[52] I. c. s. I. am, "Day 14: Recurrent Neural Network (RNN)."
[53] L. S. s. T. B. Club, "The Vanishing Gradient Problem of RNN."
[54] A. I. S. A. I. a. A. L. Science, "GRU."
[55] S.-H. Noh, "Analysis of gradient vanishing of RNNs and performance comparison," Information, vol. 12, no. 11, p. 442, 2021.
[56] J. Bergstra and Y. Bengio, "Random search for hyper-parameter optimization," Journal of machine learning research, vol. 13, no. 2, 2012.
[57] R. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection," in Ijcai, 1995, vol. 14, no. 2: Montreal, Canada, pp. 1137-1145.
[58] H. Shimodaira, "Improving predictive inference under covariate shift by weighting the log-likelihood function," Journal of statistical planning and inference, vol. 90, no. 2, pp. 227-244, 2000.
[59] S. Raschka, Python machine learning. Packt publishing ltd, 2015.
[60] P. C. Krause and C. Thomas, "Simulation of symmetrical induction machinery," IEEE transactions on power apparatus and systems, vol. 84, no. 11, pp. 1038-1053, 1965.
[61] P. C. Krause, O. Wasynczuk, S. D. Sudhoff, and S. Pekarek, Analysis of electric machinery and drive systems. Wiley Online Library, 2002.
[62] C.-M. Ong, "Dynamic simulation of electric machinery: using MATLAB/SIMULINK," (No Title), 1998.
[63] M. Verhaegen and V. Verdult, Filtering and system identification: a least squares approach. Cambridge university press, 2007.
[64] L. A. Amézquita-Brooks, J. Licéaga-Castro, E. Licéaga-Castro, and C. E. Ugalde-Loo, "Induction motor control: multivariable analysis and effective decentralized control of stator currents for high-performance applications," IEEE Transactions on Industrial Electronics, vol. 62, no. 11, pp. 6818-6832, 2015.
[65] P. Van Overschee and B. De Moor, Subspace identification for linear systems: Theory—Implementation—Applications. Springer Science & Business Media, 2012.
[66] B. De Moor, P. Van Overschee, and W. Favoreel, "Algorithms for subspace state-space system identification: an overview," Applied and Computational Control, Signals, and Circuits: Volume 1, pp. 247-311, 1999.
[67] 張竣閔, "基於擴展派克向量模數與支持向量機之感應馬達故障診斷。," 國立臺灣科技大學機械工程系碩士論文，台北市。 2021.
[68] S. Haykin and N. Network, "A comprehensive foundation," Neural networks, vol. 2, no. 2004, p. 41, 2004.
[69] H. Rahmanifard and T. Plaksina, "Application of artificial intelligence techniques in the petroleum industry: a review," Artificial Intelligence Review, vol. 52, no. 4, pp. 2295-2318, 2019.
[70] O. Araque, I. Corcuera-Platas, J. F. Sánchez-Rada, and C. A. Iglesias, "Enhancing deep learning sentiment analysis with ensemble techniques in social applications," Expert Systems with Applications, vol. 77, pp. 236-246, 2017.
[71] O. I. Abiodun, A. Jantan, A. E. Omolara, K. V. Dada, N. A. Mohamed, and H. Arshad, "State-of-the-art in artificial neural network applications: A survey," Heliyon, vol. 4, no. 11, 2018.
[72] M. A. Boyacioglu, Y. Kara, and Ö. K. Baykan, "Predicting bank financial failures using neural networks, support vector machines and multivariate statistical methods: A comparative analysis in the sample of savings deposit insurance fund (SDIF) transferred banks in Turkey," Expert Systems with Applications, vol. 36, no. 2, pp. 3355-3366, 2009.
[73] J. Mahanta, "Introduction to neural networks, advantages and applications," Towards Data Science, vol. 13, 2017.
[74] B. Samanta, "Gear fault detection using artificial neural networks and support vector machines with genetic algorithms," Mechanical systems and signal processing, vol. 18, no. 3, pp. 625-644, 2004.
[75] Lu1zero9, "深度學習隨筆——RNN/LSTM/GRU."
[76] A. I. S. A. I. a. A. L. Science, "LSTM."