本研究結合卷積雙向循環時間網路與深度卷積生成對抗網路，並應用於電動機故障聲紋辨識預警系統的開發，旨在提前識別電動機可能出現的故障類型及其嚴重程度。本研究方法首先使用短時傅立葉轉換將故障音頻信號為聲譜圖，然後採用卷積雙向循環時間網路模型，同時運用深度卷積生成對抗網路產生多樣化數據進行電動機故障鑑別之模型訓練。而為驗證所提方法的可行性，本研究分別在不同故障情境下進行測試，包括電動機軸承故障、風扇故障、電源欠相、軸心偏移以及軸承故障程度，實驗結果顯示，本文所提方法確有助於達成高準確度之故障分類判定，可協助早期掌握可能發生之故障情形，裨於提升電動機之運轉效能及可靠度。

This study combines the convolutional bidirectional recurrent time networks with deep convolutional generative adversarial networks and applies them to the development of an electric motor fault identification and early warning system. The aim is to identify potential fault types and their severity in electric motors in advance. The research method first uses short-time Fourier transform to convert fault audio signals into spectrograms. Then, a convolutional bidirectional recurrent network model consisting of convolutional neural networks and recurrent neural networks is used and trained for electric motor fault identification using diversified data generated by deep convolutional generative adversarial networks. To confirm the feasibility of the proposed method, this study conducted tests under different fault scenarios, including motor bearing faults, fan faults, power undervoltage, shaft misalignment, and bearing fault severity. The experimental results show that the proposed method helps to achieve high accuracy in fault classification, assisting in the early detection of potential faults, and improving the operational performance and reliability of electric motors.

[1]M. F. Shaikh, J. Park, and S. B. Lee, “A non-intrusive leakage flux-based method for detecting rotor faults in the starting transient of salient pole synchronous motors,” IEEE Transactions on Energy Conversion, vol. 36, no. 2, pp. 1262-1270, June 2021.
[2]P. F. Albrecht, J. C. Appiarius, R. M. McCoy, E. L. Owen, and D. K. Sharma, “Assessment of the reliability of motors in utility applications-updated,” IEEE Transactions on Energy Conversion, vol. 1, no. 1, pp. 39-46, January 1986.
[3]D. Li, W. Wang, and F. Ismail, “A spectrum synch technique for induction motor health condition monitoring,” IEEE Transactions on Energy Conversion, vol. 30, no. 4, pp. 1348-1355, July 2015.
[4]Q. Qian, H. Pu, T. Tu, and Y. Qin, “Variance discrepancy representation: A vibration characteristic-guided distribution alignment metric for fault transfer diagnosis,” Mechanical Systems and Signal Processing, vol. 217, Art. no. 111544, August 2024.
[5]H. Tang, J. Di, Z. Wu, and W. Li, “Temperature analysis for the asymmetric six-phase permanent magnet synchronous motor in healthy and fault-tolerant modes,” IEEE Transactions on Industrial Electronics, vol. 70, no. 7, pp. 6482-6493, July 2023.
[6]F. Ochando, J. I. Guerrero, J. Luque, and C. Leon, “Engine and oil condition analysis using a hybrid supervised model with a multilayer neural network and expert rules,” IEEE Transactions on Industrial Informatics, vol. 20, no. 10, pp. 11731-11739, October 2024.
[7]S. Sameh and Z. Lachiri, “Multiclass support vector machines for environmental sounds classification in visual domain based on log-Gabor filters,” International Journal of Speech Technology, vol. 16, no. 2, pp. 203-213, June 2013.
[8] Y. T. Peng, C. Y. Lin, M. T. Sun, and K. C. Tsai, “Healthcare audio event classification using hidden Markov models and hierarchical hidden Markov models,” Proceedings of IEEE International Conference on Multimedia and Expo, New York, USA, pp. 1218-1221, July 2009.
[9]G. Shen, Q. Nguyen, and J. S. Choi, “An environmental sound source classification system based on mel-frequency cepstral coefficients and Gaussian mixture models,” IFAC Proceedings Volumes, vol. 45, no. 6, pp. 1802-1807, May 2012.
[10] J. Salamon and J. P. Bello, “Deep convolutional neural networks and data augmentation for environmental sound classification,” IEEE Signal Processing Letters, vol. 24, no. 3, pp. 279-283, March 2017.
[11] S. Adapa, “Urban sound tagging using convolutional neural networks,” in Proc. DCASE2019 Challenge Technical Report Workshop, Amsterdam, Netherlands, pp. 5-9, September 2019.
[12] Y. Aytar, C. Vondrick, and A. Torralba, “SoundNet: Learning sound representations from unlabeled video,” Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain, pp. 892-900, October 2016.
[13] T. H. Vu and J. C. Wang, “Acoustic scene and event recognition using recurrent neural networks,” DCASE, vol. 2016, pp. 1-3, September 2016.
[14] J. Wang, Y. Yang, J. Mao, Z. Huang, C. Huang, and W. Xu, “CNN-RNN: A unified framework for multi-label image classification,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas , USA, pp. 2285-2294, June 2016.
[15] Z. Zuo, G. Wang, B. Shuai, L. Khan, and J. Fan, “Convolutional recurrent neural networks: Learning spatial dependencies for image representation,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 18-26, June 2015.
[16] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” Communications of the ACM, vol. 63, no. 11, pp. 139-144, June 2014.
[17] X. Chen, Z. Chen, S. Chen, L. Wang, and W. Zhai, “Unsupervised GAN with fine-tuning: A novel framework for induction motor fault diagnosis in scarcely labeled sample scenarios,” IEEE Transactions on Instrumentation and Measurement, vol. 73, no. 2 ,pp. 1-11, January 2024.
[18] B. Bahmei, E. Birmingham, and S. Arzanpour, “CNN-RNN and data augmentation using deep convolutional generative adversarial network for environmental sound classification,” IEEE Signal Processing Letters, vol. 29, pp. 1-5, January 2022.
[19] A. Radford, L. Metz, and S. Chintala, “Unsupervised representation learning with deep convolutional generative adversarial networks,” Proceedings of the 4th International Conference on Learning Representations, New York City, USA, pp. 1-16, November 2015.
[20] J. Salamon, E. Gomez, D. P. W. Ellis, and G. Richard, “Melody extraction from polyphonic music signals: Approaches, applications, and challenges,” IEEE Signal Processing Magazine, vol. 31, no. 2, pp. 118-134, March 2014.
[21] W.-L. Chu, M.-J. Xie, Q.-W. Chang, and H.-T. Yau, “Research on the recognition of machining conditions based on sound and vibration signals of a CNC milling machine,” IEEE Sensors Journal, vol. 22, no. 7, pp. 6364-6377, July 2022.
[22] Y. Ota and M. Unoki, “Anomalous sound detection for industrial machines using acoustical features related to timbral metrics,” IEEE Access, vol. 11, pp. 70884-70897, November 2023.
[23] J. W. Dennis, “Sound event recognition in unstructured environments using spectrogram image processing,” Ph.D. dissertation, School of Computer Engineering, Nanyang Technol. Univ., Singapore, December 2014.
[24] F. Demir, D. A. Abdullah, and A. Sengur, “A new deep CNN model for environmental sound classification,” IEEE Access, vol. 8, pp. 66529-66537, December 2020.
[25] Q. Hao, J. Huang, B. Wang, and F. Zhou, “Convolutional neural network image classification method integrating classic image features,” Proceedings of the IEEE 9th International Conference on Computational Intelligence and Applications, December 2024.
[26] Y. Alkhanafseh, T. C. Akinci, E. Ayaz, and A. A. Martinez-Morales, “Advanced dual RNN architecture for electrical motor fault classification,” IEEE Access, vol. 12, pp. 2965-2976, January 2024.
[27] E. Cakir, G. Parascandolo, T. Heittola, H. Huttunen, and T. Virtanen, “Convolutional recurrent neural networks for polyphonic sound event detection,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 6, pp. 1291-1303, June 2017.
[28] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735-1780, November 1997.
[29] Z. Wang and L. Yao, “Recognition of distracted driving behavior based on improved Bi-LSTM model and attention mechanism,” IEEE Access, vol. 12, pp. 67711-67725, February 2024.
[30] S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” Proceedings of the 32nd International Conference on Machine Learning , vol. 37, pp. 448-456, July 2015.
[31] 「VTR5200 User Manual」，Philips [Online]Available:https://www.jwdigital.com/uploadfile/file/20210318/1616045872752884.pdf
[32] H. Zhou, W. Chen, L. Cheng, D. Williams, C. W. De Silva, and M. Xia, “Reliable and intelligent fault diagnosis with evidential VGG neural networks,” IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-12, February 2023.
[33] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 770-778, June 2016
[34] L. Ji, C. Fu, and W. Sun, “Soft fault diagnosis of analog circuits based on a ResNet with circuit spectrum map,” IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 68, no. 7, pp. 2841-2849, May 2021.
[35] X. Zhang, X. Zhou, M. Lin, and J. Sun, “ShuffleNet: An extremely efficient convolutional neural network for mobile devices,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848-6856, June 2018.
[36] H. Tesfai, H. Saleh, M. Al-Qutayri, M. B. Mohammad, T. Tekeste, A. Khandoker, and B. Mohammad, “Lightweight ShuffleNet-based CNN for arrhythmia classification,” IEEE Access, vol. 10, pp. 111842-111854, January 2022.
[37] S. K. Hong and Y. Lee, “Optimizing detection: Compact MobileNet models for precise Hall sensor fault identification in BLDC motor drives,” IEEE Access, vol. 12, pp. 77475-77485, May 2024.