感應馬達作為動力來源是許多機械設備的關鍵組件，對於可靠性及安全性有極高的需求。馬達的故障診斷旨在減少不必要的維護操作，對於提高馬達的可靠度及安全性發揮至關重要的作用。然而目前大部分的故障診斷方法多應用在同類型以及同功率的馬達，並且在訓練資料充裕且平衡的數據條件下方可以達到較高的故障準確率，但在實際應用情況馬達功率較大，且資料多屬健康狀態，導致訓練資料不平衡，因此大幅降低馬達故障診斷的可用性。
基於此，本文應用了兩種跨域學習，分別為域對抗轉移網路(Domain-Adversarial Training of Neural Networks, DANN)以及深度域混淆(Deep Domain Confusion, DDC)，比較其特徵擷取層並透過交叉測試，並進行跨容量及跨負載測試，以驗證馬達跨域故障診斷的可行性。首先，購買2馬力及5馬力各5部的感應電動機，除了一部做為健康運轉馬達外，各製作四種不同瑕疵的試驗模型，於動力測試平台擷取不同負載下的振動加速訊號。其次，運用LeNet及AxleNet之特徵擷取架構與時頻轉換分析2馬力及5馬力的故障診斷的有效性。再者，進一步驗證馬達跨負載、跨容量與綜合跨負載/容量跨域故障診斷之成效。最後，為考量到實際應用上的訓練資料不平衡，本研究使用下採樣(Downsampling)、過採樣(Oversampling)以及混和採樣(Mixed sampling)的平衡方法，解決資料不平衡對於跨域故障診斷之問題。
實驗結果顯示，在馬達跨域故障診斷之特徵擷取架構的案例，綜合跨負載/容量的測試中對於半載以及滿載分別也有74%以70%的準確率。考量到實際應用上的資料不平衡，本研究將各類馬達故障與健康的資料不平衡比例定為1:10，結果顯示過採樣的方法並應用深度卷積生成對抗網路（Deep Convolutional Generative Adversarial Networks, DCGANs）於跨域故障診斷之成效較優，在同負載跨容量中準確率高達75%，並且在綜合跨負載的測試中也有高達74%準確率。證實本研究提出混合型特徵擷取及轉移學習模型於不平衡訓練資料之馬達跨域故障診斷之可行性及優越性。

As a power source, the induction motor is a key component of much mechanical equipment, which has extremely high requirements for reliability and safety. The purpose of motor fault diagnosis is to reduce unnecessary maintenance operations and play a vital role in improving the reliability and safety of the motor. However, most of the current fault diagnosis methods are mostly applied to motors of the same type and power, and high accuracy in fault diagnosis can be achieved under the condition of abundant and balanced training data. Nevertheless, in practical applications, the motor wattage is large, and most of the data is in a healthy state, resulting in an imbalance of training data, which greatly reduces the availability of motor fault diagnosis.
Based on this, this dissertation applies two kinds of cross-domain learning models, namely Domain-Adversarial Training of Neural Networks (DANN) and Deep Domain Confusion (DDC), to compare their feature extraction layers and pass Cross-test, and carry out cross-capacity and cross-load tests to verify the feasibility of motor cross-domain fault diagnosis. First, five induction motors of 2 horsepower and 5 horsepower were purchased. Except one was used as a healthy motor, four test models with different defects were made, and the vibration acceleration signals under different loads were captured on the power test platform. Secondly, the feature extraction architecture and time-frequency conversion of LeNet and AlexNet are used to analyze the effectiveness of fault diagnosis of 2-horsepower and 5-horsepower motors. Furthermore, further verify the effectiveness of motor cross-load, cross-capacity, and comprehensive cross-load/capacity cross-domain fault diagnosis. Finally, in order to consider the imbalance of training data in practical applications, this dissertation uses the balanced methods of downsampling, oversampling, and mixed sampling to solve the problem of data imbalance for cross-domain fault diagnosis.
The experimental results show that in the case of the feature extraction architecture for motor cross-domain fault diagnosis, the comprehensive cross-load/capacity test also has an accuracy of 74% and 70% for half-load and full-load respectively. Considering the data imbalance in practical applications, this dissertation sets the ratio of data imbalance between various motor failures and health to 1:10. The results show that the method of oversampling and the application of deep convolutional generative adversarial network (Deep Convolutional Generative Adversarial Network) Networks, DCGANs) have better results in cross-domain fault diagnosis, with an accuracy rate of up to 75% in the same load and cross-capacity test, and up to 74% in the comprehensive cross-load test. The feasibility and superiority of the hybrid feature extraction and transfer learning model proposed in this dissertation for motor cross-domain fault diagnosis of imbalanced training data are confirmed.

[1] M. Z. Ali, M. N. S. K. Shabbir, X. Liang, Y. Zhang and T. Hu, "Machine Learning-Based Fault Diagnosis for Single- and Multi-Faults in Induction Motors Using Measured Stator Currents and Vibration Signals," IEEE Trans. Ind. Appl, vol. 55, no. 3, pp. 2378-2391, 2019.
[2] V. N. Ghate and S. V. Dudul, "Cascade Neural-Network-Based Fault Classifier for Three-phase Induction Motor", IEEE Trans. Ind. Electron., vol. 58, no. 5, pp. 1555-1563, 2011.
[3] S. S. Roy, S. Dey and S. Chatterjee, "Autocorrelation Aided Random Forest Classifier-Based Bearing Fault Detection Framework," IEEE Sens. J, vol. 20, no. 18, pp. 10792-10800, 2020.
[4] S. Shao, R. Yan, Y. Lu, P. Wang and R. X. Gao, "DCNN-Based Multi-Signal Induction Motor Fault Diagnosis," IEEE Trans Instrum Meas, vol. 69, no. 6, pp. 2658-2669, Jun. 2020.
[5] H. C. Cho, J. Knowles, M. S. Fadali and K. S. Lee, "Fault Detection and Isolation of Induction Motors Using Recurrent Neural Networks and Dynamic Bayesian Modeling," IEEE Trans. on Control Systems Technology, vol. 18, no. 2, pp. 430-437, March 2010.
[6] E. Principi, D. Rossetti, S. Squartini and F. Piazza, "Unsupervised Electric Motor Fault Detection by Using Deep Autoencoders," IEEE/CAA Journal of Automatica Sinica, vol. 6, no. 2, pp. 441-451, March 2019.
[7] S. Nandi, H. A. Toliyat and X. Li, "Condition Monitoring and Fault Diagnosis of Electrical Motors—A Review," IEEE Trans. on Energy Conversion, vol. 20, no. 4, pp. 719-729, Dec. 2005.
[8] "Report of Large Motor Reliability Survey of Industrial and Commercial Installations, Part II," IEEE Trans. Ind. Appl, vol. IA-21, no. 4, pp. 865-872, July 1985.
[9] P. Zhang, Y. Du, T. G. Habetler and B. Lu, "A Survey of Condition Monitoring and Protection Methods for Medium-Voltage Induction Motors", IEEE Trans. Ind. Appl., vol. 47, no. 1, pp. 34-46, Feb. 2011.
[10] M. E. H. Benbouzid and G. B. Kliman, "What Stator Current Processing-Based Technique to use for Induction Motor Rotor Faults Diagnosis", IEEE Trans. Energy Convers, vol. 18, no. 2, pp. 238-244, Jun. 2003.
[11] A. H. Bonnett and G. C. Soukup, "Cause and Analysis of Stator and Rotor Failures in Three-Phase Squirrel-Cage Induction Motors", IEEE Trans. Ind. Appl., vol. 28, no. 4, pp. 921-937, Aug. 1992.
[12] S. Shao, S. McAleer, R. Yan and P. Baldi, "Highly Accurate Machine Fault Diagnosis Using Deep Transfer Learning," IEEE Trans. on Industrial Informatics, vol. 15, no. 4, pp. 2446-2455, April 2019.
[13] S. M. K. Zaman, H. U. M. Marma and X. Liang, "Broken Rotor Bar Fault Diagnosis for Induction Motors Using Power Spectral Density and Complex Continuous Wavelet Transform Methods", 2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE), 2019, pp. 1-4.
[14] A. Saghafinia, S. Kahourzade, A. Mahmoudi, W. P. Hew and M. N. Uddin, "On Line Trained Fuzzy Logic and Adaptive Continuous Wavelet Transform Based High Precision Fault Detection of IM with Broken Rotor Bars", 2012 IEEE Industry Applications Society Annual Meeting, 2012, pp. 1-8.
[15] Gao, D., Zhu, Y., Wang, X., Yan, K., & Hong, J.. A fault diagnosis method of rolling bearing based on complex morlet CWT and CNN. In 2018 Prognostics and System Health Management Conference (PHM-Chongqing) Oct. 2018, pp. 1101-1105.
[16] B. Chen, Z. Zhang, C. Sun, B. Li, Y. Zi and Z. He, "Fault Feature Extraction of Gearbox by Using Overcomplete Rational Dilation Discrete Wavelet Transform on Signals Measured from Vibration Sensors", Mech. Syst. Signal Process., vol. 33, pp. 275-298, 2012.
[17] J. Antoni, "Fast Computation of the Kurtogram for the Detection of Transient Faults", Mech. Syst. Signal Process., vol. 21, no. 1, pp. 108-124, 2007.
[18] B. Yang, R. Liu and X. Chen, "Fault Diagnosis for Wind Turbine Generator Bearing Via Sparse Representation and Shift-Invariant K-SVD", IEEE Trans. Ind. Informat., vol. 13, no. 3, pp. 1321-1331, Jun. 2017.
[19] B. Yang, R. Liu and X. Chen, "Sparse Time-Frequency Representation for Incipient Fault Diagnosis of Wind Turbine Drive Train", IEEE Trans. Instrum. Meas., vol. 67, no. 11, pp. 2616-2627, Nov. 2018.
[20] R. Liu, G. Meng, B. Yang, C. Sun and X. Chen, "Dislocated Time Series Convolutional Neural Architecture: An Intelligent Fault Diagnosis Approach for Electric Machine", IEEE Trans. Ind. Informat., vol. 13, no. 3, pp. 1310-1320, Jun. 2017.
[21] M. Gan et al., "Construction of Hierarchical Diagnosis Network Based on Deep Learning and its Application in the Fault Pattern Recognition of Rolling Element Bearings", Mech. Syst. Signal Process., vol. 72, pp. 92-104, 2016.
[22] J. Yang, J. Liu, J. Xie, C. Wang and T. Ding, "Conditional GAN and 2-D CNN for Bearing Fault Diagnosis With Small Samples," IEEE Trans Instrum Meas, vol. 70, pp. 1-12, 2021.
[23] Y. Qin, X. Wang and J. Zou, "The Optimized Deep Belief Networks with Improved Logistic Sigmoid units and their Application in Fault Diagnosis for Planetary Gearboxes of Wind Turbines", IEEE Trans. Ind. Electron., vol. 66, no. 5, pp. 3814-3824, May 2019.
[24] M. Zhao, M. Kang, B. Tang and M. Pecht, "Multiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis", IEEE Trans. Ind. Electron., vol. 66, no. 6, pp. 4696-4706, Jun. 2019.
[25] C. Shi, G. Panoutsos, B. Luo, H. Liu, B. Li and X. Lin, "Using Multiple-Feature-Spaces-Based Deep Learning for Tool Condition Monitoring in Ultraprecision Manufacturing," IEEE Trans. Ind. Electron., vol. 66, no. 5, pp. 3794-3803, May 2019.
[26] Weiss, K., Khoshgoftaar, T.M. and Wang, D., "A survey of Transfer Learning," Journal of Big data, 3(1), pp.1-40, 2016.
[27] R. Zhang, H. Lee, and D. R. Radev. "Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents," In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, May 2016, San Diego, California. Association for Computational Linguistics. pp. 1512–1521.
[28] R. Johnson and T. Zhang, "Semi-supervised Convolutional Neural Networks for Text Categorization Via Region Embedding", Proc. 28th Int. Conf. Neural Inf. Process. Syst., Dec. 2015, pp. 919-927.
[29] G.-S. Xie, X.-Y. Zhang, S. Yan and C.-L. Liu, "Hybrid CNN and Dictionary-based Models for Scene Recognition and Domain Adaptation", IEEE Trans. Circuits Syst. Video Technol., vol. 27, no. 6, pp. 1263-1274, Jun 2017.
[30] Ghifary, M., Kleijn, W. B., & Zhang, M., Mengjie. Domain adaptive neural networks for object recognition. In: Pacific Rim international conference on artificial intelligence. Springer, Cham, 2014. p. 898-904.
[31] L. A. Gatys, A. S. Ecker and M. Bethge, "Image Style Transfer Using Convolutional Neural Networks", Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 2414-2423.
[32] Li, Xiaodong, Weijie Mao, and Wei Jiang. "Extreme Learning Machine Based Transfer Learning for Data Classification", Neurocomputing 174, 2016, pp. 203-210.
[33] W. Lu, B. Liang, Y. Cheng, D. Meng, J. Yang and T. Zhang, "Deep Model Based Domain Adaptation for Fault Diagnosis", IEEE Trans. Ind. Electron., vol. 64, no. 3, pp. 2296-2305, Mar. 2017.
[34] Wang J, Li S, An Z, Jiang X, Qian W, Ji S. "Batch-normalized Deep Neural Networks for Achieving Fast Intelligent Fault Diagnosis of Machines," Neurocomputing, 329, pp.53-65, Feb. 2019.
[35] Elreedy D, Atiya AF. A Comprehensive "Analysis of Synthetic Minority Oversampling Technique (SMOTE) for Handling Class Imbalance," Information Sciences, 505, pp.32-64, Dec. 2019.
[36] Douzas G, Bacao F, Last F. "Improving Imbalanced Learning Through a Heuristic Oversampling Method Based on k-means and SMOTE," Information Sciences, 465, pp.1-20 Oct. 2018.
[37] Mao W, He L, Yan Y, Wang J. Online "Sequential Prediction of Bearings Imbalanced Fault Diagnosis by Extreme Learning Machine," Mechanical Systems and Signal Processing. 83, pp. 450-473. Jan. 2017.
[38] Duan L, Xie M, Bai T, Wang J. "A new Support Vector Data Description Method for Machinery Fault Diagnosis with Unbalanced Datasets," Expert Systems with Applications. 64, pp.239-246. Dec. 2016.
[39] Jia F, Lei Y, Lu N, Xing S. "Deep Normalized Convolutional Neural Network for Imbalanced Fault Classification of Machinery and its Understanding via Visualization", Mechanical Systems and Signal Processing. 110, pp.349-367. Sep. 2018.
[40] Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. "Generative Adversarial Nets," Communications of the ACM, 2020, pp. 139-144.
[41] Y. Yuan, C. Tian and X. Lu, "Auxiliary Loss Multimodal GRU Model in Audio-visual Speech Recognition", IEEE Access, vol. 6, pp. 5573-5583, 2018.
[42] R. Togo, T. Ogawa and M. Haseyama, "Synthetic Gastritis Image Generation via Loss Function-based Conditional PGGAN", IEEE Access, vol. 7, pp. 87448-87457, 2019.
[43] Li Y, Pan Q, Wang S, Yang T, Cambria E. "A generative Model for Category Text Generation, " Information Sciences. 450, pp.301-315, Jun. 2018.
[44] Radford A, Metz L, Chintala S. "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks", arXiv preprint arXiv:1511.06434. 2015 Nov.
[45] P. L. Suárez, A. D. Sappa and B. X. Vintimilla, "Infrared Image Colorization Based on a Triplet DCGAN Architecture", Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops, Jul. 2017, pp. 212-217.
[46] Z. Chun, W. Hanli, W. Tianyuan and W. Wei, "Speech Generation Based on Depth Convolution for Adversarial Networks", Instrum. Technol., no. 2, pp. 13-15, 2018.
[47] Fernández, A., García, S., Galar, M., Prati, R.C., Krawczyk, B., Herrera, F.. "Foundations on Imbalanced Classification. In: Learning from Imbalanced Data Sets", Springer, Cham. Oct. 2018.
[48] S. J. Pan and Q. Yang, "A Survey on Transfer Learning," in IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, Oct. 2010.
[49] Tzeng, Eric, et al. "Deep Domain Confusion: Maximizing for Domain Invariance," arXiv preprint arXiv:1412.3474 (2014).
[50] Ganin, Yaroslav, et al. "Domain-Adversarial Training of Neural Networks", The journal of machine learning research, 17.1, pp.2096-2030 2016.
[51] FERNÁNDEZ, Alberto, et al. "Foundations on imbalanced classification," In: Learning from Imbalanced Data Sets. Springer, Cham, 2018. p. 19-46.
[52] BARANDELA, Ricardo, et al. "Strategies for learning in class imbalance problems," Pattern Recognition, 2003, 36.3: pp.849-851.
[53] Lin, Y., Lee, Y., Wahba, G. "Support Vector Machines for Classification in Nonstandard Situations," Mach. Learn. 46, pp.191–202, 2002.
[54] Liu, B., Ma, Y., Wong, C.: Improving an Association Rule Based Classifier. In: Zighed, D., Komorowski, J., Zytkow, J. (eds.) Principles of Data Mining and Knowledge Discovery. LNCS, vol. 1910, pp. 293–317. Springer, Berlin/Heidelberg (2000)Return to ref 50 in article.
[55] M. Galar, A. Fernandez, E. Barrenechea, H. Bustince and F. Herrera, "A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches," IEEE Trans. on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 42, no. 4, pp. 463-484, July 2012.
[56] Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. "SMOTE: Synthetic Minority Over-sampling Technique," Journal of artificial intelligence research. 16, pp.321-357, Jun. 2002.
[57] M. Lin, K. Tang and X. Yao, "Dynamic Sampling Approach to Training Neural Networks for Multiclass Imbalance Classification," IEEE Trans. on Neural Networks and Learning Systems, vol. 24, no. 4, pp. 647-660, April 2013.
[58] N. Japkowicz and S. Stephen, "The class imbalance problem: A Systematic Study," Intell. Data Anal., vol. 6, no. 5, pp. 429-449, 2002.
[59] Y. Sun, M. S. Kamel, A. Wong and Y. Wang, "Cost-sensitive Boosting for Classification of Imbalanced Data," Pattern Recogn, vol. 40, no. 12, pp. 3358-3378, 2007.
[60] Y. Sun, M. S. Kamel and Y. Wang, "Boosting for Learning Multiple Classes with Imbalanced Class Distribution", Proc. Int. Conf. Data Min., 2006, pp. 592-602.
[61] Y. Huang, Y. Jin, Y. Li and Z. Lin, "Towards Imbalanced Image Classification: A Generative Adversarial Network Ensemble Learning Method," IEEE Access, vol. 8, pp. 88399-88409, 2020.
[62] Y. Wang and H. Li, "A novel Intelligent Modeling Framework Integrating Convolutional Neural Network with an Adaptive Time-series Window and its Application to Industrial Process Operational Optimization," Chemometric Intell. Lab. Syst., vol. 179, pp. 64-72, Aug. 2018.
[63] A. Creswell, T. White, V. Dumoulin, K. Arulkumaran, B. Sengupta and A. A. Bharath, "Generative Adversarial Networks: An Overview," IEEE Signal Process. Mag., vol. 35, no. 1, pp. 53-65, Jan. 2018.
[64] A. Radford, L. Metz and S. Chintala, "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks," arXiv:1511.06434, 2015.