Commutator motor fault diagnosis using acoustic data with a transfer learning approach

• Autorzy: Zastępa Marek

Identyfikatory

DOI

10.15199/48.2024.12.40

Warianty tytułu

PL

Diagnostyka silników komutatorowych z wykorzystaniem danych akustycznych i transfer learning

• Języki publikacji: EN

Abstrakty

EN

In this paper, the author proposed a new method of preprocessing data called High Contrast Frequency Maps with Lowpass Filter (HCFMwLF) for the pre-trained neural networks in commutator motor fault recognition. The broken rotor coil, the four drilled holes in the front bearing, the short-circuit in stator wiring, the broken fan, the broken gear tooth and broken gear in comparison with healthy commutator motor were studied. As a result, the GoogLeNet, ResNet-50, and VGG-19 performed 100% efficiency.

PL

W tym artykule, autor przedstawia nową metodę preprocessingu danych zwaną High Contrast Frequency Maps with Lowpass Filter (HCFMwLF) dla wstępnie wytrenowanych sieci neuronowych w klasyfikacji uszkodzeń silników elektrycznych. Przerwa w obwodzie wirnika, cztery wywiercone otwory w przednim łożysku, zwarcie w obwodzie stojana, uszkodzony wiatrak, uszkodzony ząb koła zębatego, uszkodzona przekładnia w porównaniu do zdrowego silnika zostały zbadane. W rezultacie, sieci GoogLeNet, ResNet-50 i VGG-19 uzyskały 100% dokładności.

Słowa kluczowe

EN

electric motor; diagnostic; transfer learning; deep learning

PL

silnik elektryczny; diagnostyka; transfer learning; uczenie głębokie

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2024
• Tom: R. 100, nr 12
• Strony: 173--180
• Opis fizyczny: Bibliogr. 30 poz., rys., tab.

Twórcy

autor

Zastępa Marek

• AGH University of Krakow, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, Department of Automatic Control and Robotics, al. A. Mickiewicza 30, 30-059 Krakow, Poland

• https://orcid.org/0009-0006-9934-7574

Bibliografia

• [1] A. Glowacz, “Thermographic Fault Diagnosis of Shaft of BLDC Motor,” Sensors, vol. 22, no. 21, p. 8537, Nov. 2022, doi: 10.3390/s22218537.
• [2] A. Glowacz, “Thermographic Fault Diagnosis of Ventilation in BLDC Motors,” Sensors, vol. 21, no. 21, p. 7245, Oct. 2021, doi: 10.3390/s21217245.
• [3] Y. Yan, Q. Liu, X. qin Gao, "Motor Fault Diagnosis Algorithm Based on Wavelet and Attention Mechanism," Journal of Sensors, vol. 2021, p. 9, Jul. 2021. https://doi.org/10.1155/2021/3782446
• [4] W. Li, Y. Cao, L. Li, S. Hou, "An Orthogonal Wavelet Transform-Based K-Nearest Neighbor Algorithm to Detect Faults in Bearings," Shock and Vibration, vol. 2022, p. 13, Feb. 2022, https://doi.org/10.1155/2022/5242106
• [5] L. Wang, S. Ji, N. Ji, "Comparison of Support Vector Machine-Based Techniques for Detection of Bearing Faults," Shock and Vibration, vol. 2018, p. 13, Dec. 2018. https://doi.org/10.1155/2018/8174860
• [6] H. Nakamura, K. Asano, S. Usuda, and Y. Mizuno, “A Diagnosis Method of Bearing and Stator Fault in Motor Using Rotating Sound Based on Deep Learning,” Energies, vol. 14, no. 5, p. 1319, Mar. 2021, doi: 10.3390/en14051319.
• [7] H. Santos, P. Scalassara, W. Endo, A. Goedtel, J. Guedes, M. Gentil, “Non-invasive sound-based classifier of bearing faults in electric induction motors,” IET Science, Measurement & Technology, vol. 15, pp. 434-445, Jul. 2021, https://doi.org/10.1049/smt2.12044
• [8] A. Glowacz, “Recognition of Acoustic Signals of Commutator Motors,” Applied Sciences, vol. 8, no. 12, p. 2630, Dec. 2018, doi: 10.3390/app8122630.
• [9] G. Yang, Y. Wei, H. Li, "Acoustic Diagnosis of Rolling Bearings Fault of CR400 EMU Traction Motor Based on XWT and GoogleNet," Shock and Vibration, vol. 2022, p 12, Nov. 2022. https://doi.org/10.1155/2022/2360067
• [10] X. Zhang, B. Wang, X. Chen, “Intelligent fault diagnosis of roller bearings with multivariable ensemble-based incremental support vector machine,” Knowledge-Based Systems, vol. 89, p. 56-85, Nov. 2015, https://doi.org/10.1016/j.knosys.2015.06.017
• [11] L. Hu, J. Cui, “Digital image recognition based on Fractionalorder- PCA-SVM coupling algorithm,” Measurement, vol. 145, p. 150-159, Oct. 2019, https://doi.org/10.1016/j.measurement.2019.02.006
• [12] Z. Du, J. Ma, C. Ma, M. Huang, W. Sun, "Weighted Reconstruction and Improved Eigenclass Combination Method for the Detection of Bearing Faults", Mathematical Problems in Engineering, vol. 2021, p. 11, Nov. 2021. https://doi.org/10.1155/2021/5503107
• [13] S. Shan, J. Liu, S. Wu, Y. Shao, H. Li, “A motor bearing fault voiceprint recognition method based on Mel-CNN model,” Measurement, vol. 207, pp 112408, Feb. 2023, https://doi.org/10.1016/j.measurement.2022.112408
• [14] J. Lei, C. Liu, D. Jiang, „Fault diagnosis of wind turbine based on Long Short-term memory networks,” Renewable Energy, vol. 133, p. 422-432, Apr. 2019, https://doi.org/10.1016/j.renene.2018.10.031
• [15] S. Hao, F.-X. Gao, Y. Li, J. Jiang, “Multisensor bearing fault diagnosis based on one-dimensional convolutional long shortterm memory networks,” Measurement, vol. 159, pp. 107802, Jul. 2020, https://doi.org/10.1016/j.measurement.2020.107802
• [16] M. Wang, B. Guo, Y. Hu, Z. Zhao, C. Liu, and H. Tang, “Transfer Learning Models for Detecting Six Categories of Phonocardiogram Recordings,” Journal of Cardiovascular Development and Disease, vol. 9, no. 3, p. 86, Mar. 2022, doi: 10.3390/jcdd9030086
• [17] E. Tsalera, A. Papadakis, and M. Samarakou, “Comparison of Pre-Trained CNNs for Audio Classification Using Transfer Learning,” Journal of Sensor and Actuator Networks, vol. 10, no. 4, p. 72, Dec. 2021, doi: 10.3390/jsan10040072
• [18] P. C. Sen, Principles of Electric Machines and Power Electronics, Chennai, India: Jon Wiley & Sons, 2013, pp. 397
• [19] R. B. Randall, J. Antoni, “Rolling element bearing diagnostics - A tutorial,” Mechanical Systems and Signal Processing, vol. 24, issue 2, pp. 485-520, Feb. 2011, https://doi.org/10.1016/j.ymssp.2010.07.017
• [20] P. A. Delgado-Arredondo, D. Morinigo-Sotelo, R. A. Osornio- Rios, J. G. Avina-Cervantes, H. Rostro-Gonzalez, R. de J. Romero-Troncoso, “Methodology for fault detection in induction motors via sound and vibration signals,” Mechanical Systems and Signal Processing, vol. 83, pp. 568-589, Jan. 2017, https://doi.org/10.1016/j.ymssp.2016.06.032
• [21] B. Benedik, J. Rihtaršič, J. Povh, J. Tavčar, “Failure modes and life prediction model for high-speed bearings in a throughflow universal motor,” Engineering Failure Analysis, vol. 128, p. 105535, Oct. 2021, https://doi.org/10.1016/j.engfailanal.2021.105535
• [22] I. Goodfellow, Y. Bengio, A. Courville, “Convolutional Network” in Deep Learning, MIT Press, 2016, pp. 327-330, [Online], https://www.deeplearningbook.org/, accessed May 2024
• [23] Z. Guo, M. Yang, X. Huang, “Bearing fault diagnosis based on speed signal and CNN model,” Energy Reports, vol. 8, supplement 13, p. 904-913, Nov. 2022, https://doi.org/10.1016/j.egyr.2022.08.041
• [24] M. Skowron, “Application of deep learning neural networks for the diagnosis of electrical damage to the induction motor using the axial flux,” Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 68, no. 5, pp. 1031-1038, Oct. 2020, DOI: 10.24425/bpasts.2020.134664
• [25] T. Saghi, D. Bustan, and S. S. Aphale, “Bearing Fault Diagnosis Based on Multi-Scale CNN and Bidirectional GRU,” Vibration, vol. 6, no. 1, pp. 11–28, Dec. 2022, doi: 10.3390/vibration6010002
• [26] J. Yosinski, J. Clune, Y. Bengio, H. Lipson, “How transferable are features in deep neural networks?,” arXiv: Advances in Neural Information Processing Systems 27, pp. 3320-3328, Dec. 2014, https://doi.org/10.48550/arXiv.1411.1792
• [27] TensorFlow documentation, Article “Transfer learning and fine-tuning,” https://www.tensorflow.org/guide/keras/transfer_learning?hl=en , accessed May 2024
• [28] M. J. Hasan, M. Sohaib, and J.-M. Kim, “A Multitask-Aided Transfer Learning-Based Diagnostic Framework for Bearings under Inconsistent Working Conditions,” Sensors, vol. 20, no. 24, p. 7205, Dec. 2020, doi: 10.3390/s20247205
• [29] MathWorks documentation, Articles: “googlenet”, “resnet50”, “vgg19”, https://www.mathworks.com/, accessed May 2024
• [30] P. Ramachandran, B. Zoph, Q. V. Le, „Searching for Activation Functions,” arXiv, Oct. 2017, https://doi.org/10.48550/arXiv.1710.05941

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).