دسته‌بندی شدت عیب اتصال کوتاه بین دور موتورهای سنکرون مغناطیس دائم با استفاده از درخت تصمیم گیری و شبکه عصبی بیزین

چکیده مقاله :

این مقاله به بررسی شناسایی شدت عیب اتصال کوتاه بین دور در یک موتور سنکرون مغناطیس دائم با توان ۳ کیلووات با استفاده از درخت تصمیم‌گیری و شبکه عصبی عمیق بیزین می‌پردازد. مجموعه داده اصلی شامل سیگنال‌های جریان سه‌فاز در شرایط سالم و دارای عیب بوده که شش سطح از شدت عیب را شامل می‌شود. یک مرحله پیش‌پردازش برای تحلیل داده‌ها در حوزه‌های زمان و فرکانس انجام می‌شود. در این فرآیند از تبدیل موجک گسسته  و تحلیل چگالی طیفی توان استفاده شده است. برای کاهش ابعاد فضای آموزشی، ابتدا معیارهای آماری مانند میانگین، انحراف معیار، کشیدگی و چولگی به دست می‌آیند. سپس از تحلیل مولفه‌های اصلی کرنل برای تعیین برجسته‌ترین ویژگی‌ها استفاده می‌شود. الگوریتم درخت تصمیم‌گیری برای شناسایی وضعیت عیب موتور آموزش داده می‌شود. در نهایت،یک شبکه عصبی عمیق مبتنی بر تئوری بیزین برای تشخیص شدت عیب اتصال کوتاه بین دور به کار گرفته می‌شود. عملکرد الگوریتم پیشنهادی از نظر دقت، صحت، بازخوانی و امتیاز 1F با در نظر گرفتن تعداد متفاوتی از ویژگی‌های غالب منتخب ارزیابی می‌شود.

چکیده انگلیسی :

This paper investigates the identification of inter-turn short-circuit fault severity in a 3-kilowatt permanent magnet synchronous motor using a decision tree and a deep Bayesian neural network. The primary dataset includes three-phase current signals under both healthy and faulty conditions, covering six fault severity levels. A preprocessing stage is conducted to analyze the data in time and frequency domains using discrete wavelet transform and power spectral density analysis. To reduce the dimensionality of the feature space, statistical indicators such as mean, standard deviation, kurtosis, and skewness are initially extracted. Kernel principal component analysis is then employed to identify the most salient features. A decision tree algorithm is trained to detect motor fault conditions. Finally, a deep Bayesian neural network is applied to classify the severity of the inter-turn short-circuit fault. The proposed algorithm’s performance is evaluated in terms of accuracy, precision, recall, and F1-score, considering varying numbers of selected dominant features.

منابع و مأخذ:


[1] Bhuiyan, E. A., Akhand, M. M. A., Das, S. K., Ali, M. F., Tasneem, Z., Islam, M. R., ... & Moyeen, S. I. (2020). A survey on fault diagnosis and fault tolerant methodologies for permanent magnet synchronous machines. International Journal of Automation and Computing, 17, 763-787.#
[2] Kilic, A., & Weiss, F. (2023). Early detection of PMSM faults at static and dynamic operating points by using artificial neural network for automated electric vehicle. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 45(9), 493.#
[3] Chen, X., Qin, P., Chen, Y., Zhao, J., Li, W., Mao, Y., & Zhao, T. (2022). Inter-turn short circuit fault diagnosis of PMSM. Electronics, 11(10), 1576.#
[4] Wang, D., & Chen, Y. (2020). Fault-tolerant control of coil inter-turn short-circuit in five-phase permanent magnet synchronous motor. Energies, 13(21), 5669.#
[5] Qin, Y., Li, G. J., Jia, C., & McKeever, P. (2023). Investigation of inter-turn short-circuit fault of PM machines using PWM voltage-based modeling. IEEE Transactions on Transportation Electrification, 10(1), 1324-1334.#
[6] Forstner, G., Kugi, A., & Kemmetmüller, W. (2020, August). Model-based fault identification of inter-turn winding short circuits in PMSM. In 2020 International Conference on Electrical Machines (ICEM) (Vol. 1, pp. 1390-1396). IEEE.#
[7] Niu, D., & Song, D. (2023). Model-based robust fault diagnosis of incipient ITSC for PMSM in elevator traction system. IEEE Transactions on Instrumentation and Measurement.#
[8] Sarikhani, A., & Mohammed, O. A. (2012). Inter-turn fault detection in PM synchronous machines by physics-based back electromotive force estimation. IEEE Transactions on Industrial Electronics, 60(8), 3472-3484.#
[9] Fitouri, M., Bensalem, Y., & Abdelkrim, M. N. (2016). Modeling and detection of the short-circuit fault in PMSM using Finite Element Analysis. IFAC-PapersOnLine, 49(12), 1418-1423.#
[10] Qi, Y., Bostanci, E., Gurusamy, V., & Akin, B. (2018). A comprehensive analysis of short-circuit current behavior in PMSM interturn short-circuit faults. IEEE Transactions on Power Electronics, 33(12), 10784-10793.#
[11] Li, Y., Wang, Y., Zhang, Y., & Zhang, J. (2021). Diagnosis of inter-turn short circuit of permanent magnet synchronous motor based on deep learning and small fault samples. Neurocomputing, 442, 348-358.#
[12] Li, Y., Wang, R., Mao, R., Zhang, Y., Zhu, K., Li, Y., & Zhang, J. (2023). A Fault Diagnosis Method Based on an Improved Deep Q-Network for the Inter-Turn Short Circuits of a Permanent Magnet Synchronous Motor. IEEE Transactions on Transportation Electrification.#
[13] Skowron, M., Orlowska-Kowalska, T., & Kowalski, C. T. (2022). Detection of permanent magnet damage of PMSM drive based on direct analysis of the stator phase currents using convolutional neural network. IEEE Transactions on Industrial Electronics, 69(12), 13665-13675.#
[14] Wu, X., Geng, Y., Li, M., Wang, W., & Tu, M. (2024). Inter-turn Short Circuit Diagnosis of Permanent Magnet Synchronous Motor Based on Siamese Convolutional Neural Network under Small Fault Samples. IEEE Sensors Journal.#
[15] Chen, Q., Dai, X., Song, X., & Liu, G. (2023). ITSC Fault Diagnosis for Five Phase Permanent Magnet Motors by Attention Mechanisms and Multiscale Convolutional Residual Network. IEEE Transactions on Industrial Electronics.#
[16] Shih, K. J., Hsieh, M. F., Chen, B. J., & Huang, S. F. (2022). Machine learning for inter-turn short-circuit fault diagnosis in permanent magnet synchronous motors. IEEE Transactions on Magnetics, 58(8), 1-7.#
[17] Song, Q., Wang, M., Lai, W., & Zhao, S. (2022). Multiscale kernel-based residual cnn for estimation of inter-turn short circuit fault in pmsm. Sensors, 22(18), 6870.#
[18] Wu, X., Geng, Y., Li, M., Wang, W., & Tu, M. (2024). Inter-turn Short Circuit Diagnosis of Permanent Magnet Synchronous Motor Based on Siamese Convolutional Neural Network under Small Fault Samples. IEEE Sensors Journal.#
[19] Chen, Q., Dai, X., Song, X., & Liu, G. (2023). ITSC Fault Diagnosis for Five Phase Permanent Magnet Motors by Attention Mechanisms and Multiscale Convolutional Residual Network. IEEE Transactions on Industrial Electronics.#
[20] Sun, W., Paiva, A. R., Xu, P., Sundaram, A., & Braatz, R. D. (2020). Fault detection and identification using Bayesian recurrent neural networks. Computers & Chemical Engineering, 141, 106991.#
[21] Pietrzak, P., & Wolkiewicz, M. (2022). Machine learning-based stator current data-driven PMSM stator winding fault diagnosis. Sensors, 22(24), 9668.#
[22] Song, Q., Wang, M., Lai, W., & Zhao, S. (2022). On Bayesian optimization-based residual CNN for estimation of inter-turn short circuit fault in PMSM. IEEE Transactions on Power Electronics, 38(2), 2456-2468.#
[23] Xia, Y. K., Wang, W. T., & Li, X. Y. (2024). Adaptive parameter selection Variational Mode Decomposition based on Bayesian optimization and its application to the detection of ITSC in PMSM. IEEE Access.#
[24] Song, Q., Wang, M., Lai, W., & Zhao, S. (2022). On Bayesian optimization-based residual CNN for estimation of inter-turn short circuit fault in PMSM. IEEE Transactions on Power Electronics, 38(2), 2456-2468.#
[25] Yan, G., & Hu, Y. (2024). Inter-turn short circuit and demagnetization fault diagnosis of ship PMSM based on multiscale residual dilated CNN and BiLSTM. Measurement Science and Technology, 35(4), 046105.#
[26] Mirshekali, H., Santos, A. Q., & Shaker, H. R. (2023). A survey of time-series prediction for digitally enabled maintenance of electrical grids. Energies, 16(17), 6332.#
[27] Zeng, Z., Zhang, M., Chen, L., Huang, Q., & Sun, D. (2022, October). A new method to estimate the severity of interturn short-circuit fault for PMSM. In 2022 IEEE International Conference on Power Systems and Electrical Technology (PSET) (pp. 149-154). IEEE.#
[28] Qi, Y., Zafarani, M., Gurusamy, V., & Akin, B. (2019). Advanced severity monitoring of interturn short circuit faults in PMSMs. IEEE Transactions on Transportation Electrification, 5(2), 395-404.#
[29] Huang, S., Aggarwal, A., Strangas, E. G., Khoshoo, B., Li, K., & Niu, F. (2021). Mitigation of interturn short-circuits in IPMSM by using MTPCC control adaptive to fault severity. IEEE Transactions on Power Electronics, 37(4), 4685-4696.#
[30] Qi, Y., Bostanci, E., Zafarani, M., & Akin, B. (2018). Severity estimation of interturn short circuit fault for PMSM. IEEE Transactions on Industrial Electronics, 66(9), 7260-7269.#
[31] Fan, C., Chen, M., Wang, X., Wang, J., & Huang, B. (2021). A review on data preprocessing techniques toward efficient and reliable knowledge discovery from building operational data. Frontiers in energy research, 9, 652801.#
[32] Divya, D., Marath, B., & Santosh Kumar, M. B. (2023). Review of fault detection techniques for predictive maintenance. Journal of Quality in Maintenance Engineering, 29(2), 420-441.#
[33] Alessio, S. M., & Alessio, S. M. (2016). Discrete wavelet transform (DWT). Digital signal processing and spectral analysis for scientists: concepts and applications, 645-714.#
[34] Rahi, P. K., & Mehra, R. (2014). Analysis of power spectrum estimation using welch method for various window techniques. International Journal of Emerging Technologies and Engineering, 2(6), 106-109.#
[35] Jung, W., Yun, S. H., Lim, Y. S., Cheong, S., & Park, Y. H. (2023). Vibration and current dataset of three-phase permanent magnet synchronous motors with stator faults. Data in Brief, 47, 108952.#
[36] Shen, K., Wang, H., Chaudhuri, A., & Asgharzadeh, Z. (2023, August). Automatic Gaussian Bandwidth Selection for Kernel Principal Component Analysis. In International Conference on Knowledge Science, Engineering and Management (pp. 15-26). Cham: Springer Nature Switzerland.#
[37] Breiman, L. (2017). Classification and regression trees. Routledge.#
[38] Zou, L., Zhuang, K. J., & Hu, J. (2023, March). A Bayesian Adaptive Resize-Residual Deep Learning Network for Fault Diagnosis of Rotating Machinery. In Proceedings of The 17th East Asian-Pacific Conference on Structural Engineering and Construction, 2022: EASEC-17, Singapore (pp. 783-801). Singapore: Springer Nature Singapore.#
[39] Neal, R. M. (2012). Bayesian learning for neural networks (Vol. 118). Springer Science & Business Media.#
[40] MacKay, D. J. (1992). A practical Bayesian framework for backpropagation networks. Neural computation, 4(3), 448-472.#
[41] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1), 1929-1958.#
[42] Goodfellow, I. (2016). Deep learning (Vol. 196). MIT press.#
[43] Graves, A. (2011). Practical variational inference for neural networks. Advances in neural information processing systems, 24.#