Fault Diagnosis of Induction Motors under Limited Data for Across Loading by Residual VGG-Based Siamese Network
Source abstract
Abstract
This study proposes an improved few-shot learning model of the Siamese network residual Visual Geometry Group (VGG). This model combined with time–frequency domain transformation techniques effectively enhances the performance of across-load fault diagnosis for induction motors with limited data conditions. The proposed residual VGG-based Siamese network consists of two primary components: the feature extraction network, which is the residual VGG, and the merged similarity layer. First, the residual VGG architecture utilizes residual learning to boost learning efficiency and mitigate the degradation problem typically associated with deep neural networks. The employment of smaller convolutional kernels substantially reduces the number of model parameters, expedites model convergence, and curtails overfitting. Second, the merged similarity layer incorporates multiple distance metrics for similarity measurement to enhance classification performance. For cross-domain fault diagnosis in induction motors, we developed experimental models representing four common types of faults. We measured the vibration signals from both healthy and faulty models under varying loads. We then applied the proposed model to evaluate and compare its effectiveness in cross-domain fault diagnosis against conventional AI models. Experimental results indicate that when the imbalance ratio reached 20:1, the average accuracy of the proposed residual VGG-based Siamese network for fault diagnosis across different loads was 98%, closely matching the accuracy of balanced and sufficient datasets, and significantly surpassing the diagnostic performance of other models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Non-Destructive Testing Techniques · Mineral Processing and Grinding
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei 10607, Taiwan
References (48)
Show source-provided references
1. Bi–spectrum based–EMD applied to the non–stationary vibration signals for bearing faults diagnosis10.1016/j.isatra.2014.06.002 ↗
2. Liu, H., Li, D., Yuan, Y., Zhang, S., Zhao, H., and Deng, W. (2019). Fault diagnosis for a bearing rolling element using improved VMD and HT. Appl. Sci., 9.10.3390/app9071439 ↗
3. Real–time implementation of wavelet packet transform–based diagnosis and protection of three–phase induction motors10.1109/TEC.2006.882417 ↗
4. Yang, Y., Haque, M.M.M., Bai, D., and Tang, W. (2021). Fault Diagnosis of Electric Motors Using Deep Learning Algorithms, and Its Application: A Review. Energies, 14.10.3390/en14217017 ↗
5. A deep learning approach for fault diagnosis of induction motors in manufacturing10.1007/s10033-017-0189-y ↗
6. A motor current signal–based bearing fault diagnosis using deep learning and information fusion10.1109/TIM.2019.2933119 ↗
7. DCNN–based multi–signal induction motor fault diagnosis10.1109/TIM.2019.2925247 ↗
8. Wang, C.-S., Kao, I.-H., and Perng, J.-W. (2021). Fault diagnosis and fault frequency determination of permanent magnet synchronous motor based on deep learning. Sensors, 21.10.3390/s21113608 ↗
9. ANN assisted multi sensor information fusion for BLDC motor fault diagnosis10.1109/ACCESS.2021.3050243 ↗
10. An Improved Triplet Network for Electromechanical Actuator Fault Diagnosis Based on Similarity Strategy10.1109/TIM.2022.3216413 ↗
11. Imbalanced Sample Fault Diagnosis of Rolling Bearing Using Deep Condition Multidomain Generative Adversarial Network10.1109/JSEN.2022.3222535 ↗
12. A novel class imbalance-robust network for bearing fault diagnosis utilizing raw vibration signals10.1016/j.measurement.2020.107567 ↗
13. Unsupervised domain-share CNN for machine fault transfer diagnosis from steady speeds to time-varying speeds10.1016/j.jmsy.2021.11.016 ↗
14. Mushtaq, S., Islam, M.M.M., and Sohaib, M. (2021). Deep learning aided data-driven fault diagnosis of rotatory machine: A comprehensive review. Energies, 14.10.3390/en14165150 ↗
15. Zheng, M.L., Chang, Q., Man, J.F., Liu, Y., and Shen, Y.P. (2022). Two-Stage Multi-Scale Fault Diagnosis Method for Rolling Bearings with Imbalanced Data. Machines, 10.10.3390/machines10050336 ↗
16. Hao, C., Du, J., and Liang, H. (2022). Imbalanced Fault Diagnosis of Rolling Bearing Using Data Synthesis Based on Multi-Resolution Fusion Generative Adversarial Networks. Machines, 10.10.3390/machines10050295 ↗
17. Oversampling adversarial network for class-imbalanced fault diagnosis10.1016/j.ymssp.2020.107175 ↗
18. Ramos-Pérez, I., Arnaiz-González, Á., Rodríguez, J.J., and García-Osorio, C. (2022). When is resampling beneficial for feature selection with imbalanced wide data?. Expert Syst. Appl., 188.10.1016/j.eswa.2021.116015 ↗
19. Fault diagnosis of permanent magnet motor based on DCGAN-RCCNN10.1016/j.egyr.2022.01.226 ↗
20. Diagnosis of rolling bearing based on classification for high dimensional unbalanced data10.1109/ACCESS.2019.2919406 ↗
21. WR-ELM: Weighted regularization extreme learning machine for imbalance learning in software fault prediction10.1109/TR.2020.2996261 ↗
22. Fan, Y., Cui, X., Han, H., and Lu, H. (2019). Chiller fault diagnosis with field sensors using the technology of imbalanced data. Appl. Thermal Eng., 159.10.1016/j.applthermaleng.2019.113933 ↗
23. Chang, H., Wang, Y., Shih, Y., and Kuo, C. (2022). Fault diagnosis of induction motors with imbalanced data using deep convolutional generative adversarial network. Appl. Sci., 12.10.3390/app12084080 ↗
24. Highly accurate machine fault diagnosis using deep transfer learning10.1109/TII.2018.2864759 ↗
25. Deep learning for infrared thermal image based machine health monitoring10.1109/TMECH.2017.2722479 ↗
26. Ullah, Z., Lodhi, B.A., and Hur, J. (2020). Detection and identification of demagnetization and bearing faults in PMSM using transfer learning based VGG. Energies, 13.10.3390/en13153834 ↗
27. Liu, S., Jiang, H., Wu, Z., Liu, Y., and Zhu, K. (2022). Machine fault diagnosis with small sample based on variational information constrained generative adversarial network. Adv. Eng. Inform., 54.10.1016/j.aei.2022.101762 ↗
28. Zhang, X., Wu, B., Zhang, X., Zhou, Q., Hu, Y., and Liu, J. (2022). A novel assessable data augmentation method for mechanical fault diagnosis under noisy labels. Measurement, 198.10.1016/j.measurement.2022.111114 ↗
29. Xu, J., Shi, Y., Shi, L., Ren, Z., and Lu, Y. (2022). Intelligent Deep Adversarial Network Fault Diagnosis Method Using Semisupervised Learning. Math. Probl. Eng., 2020.10.1155/2020/8503247 ↗
30. Sun, W., Zhou, J., Sun, B., Zhou, Y., and Jiang, Y. (2022). Markov transition field enhanced deep domain adaptation network for milling tool condition monitoring. Micromachines, 13.10.3390/mi13060873 ↗
31. Condition monitoring and fault diagnosis of induction motors: A review10.1007/s11831-018-9286-z ↗
32. Skóra, M., Ewert, P., and Kowalski, C.T. (2019). Selected Rolling Bearing Fault Diagnostic Methods in Wheel Embedded Permanent Magnet Brushless Direct Current Motors. Energies, 12.10.3390/en12214212 ↗
33. Bearing fault detection of IPMSMs using zoom FFT10.5370/JEET.2016.11.5.1235 ↗
34. Sanakkayala, D.C., Varadarajan, V., Kumar, N., Soni, G., Kamat, P., Kumar, S., Patil, S., and Kotecha, K. (2022). Explainable AI for Bearing Fault Prognosis Using Deep Learning Techniques. Micromachines, 13.10.3390/mi13091471 ↗
35. Time-frequency manifold as a signature for machine health diagnosis10.1109/TIM.2012.2183402 ↗
36. Effective fault diagnosis based on wavelet and convolutional attention neural network for induction motors
37. Liu, Y., Zhang, H., Zhang, W., Lu, G., Tian, Q., and Ling, N. (2022). Few-shot image classification: Current status and research trends. Electronics, 11.10.3390/electronics11111752 ↗
38. MergedNET: A simple approach for one-shot learning in siamese networks based on similarity layers10.1016/j.neucom.2022.08.070 ↗
39. Partial discharge diagnosis with siamese fusion network10.1109/ACCESS.2022.3181491 ↗
40. Simonyan, K., and Zisserman, A. (2015, January 7–9). Very deep convolutional networks for large–scale image recognition. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015—Conference Track Proceedings, San Diego, CA, USA.
41. Dong, Z., Xie, M., and Li, X.Q. (2023). Multi-Scale Receptive Fields Convolutional Network for Action Recognition. Appl. Sci., 13.10.3390/app13063403 ↗
42. Collaborative edge computing for distributed cnn inference acceleration using receptive field-based segmentation10.1016/j.comnet.2022.109150 ↗
43. Li, G., Shen, X., Li, J., and Wang, J. (2021). Diagonal-kernel convolutional neural networks for image classification. Digit. Signal Process., 108.10.1016/j.dsp.2020.102898 ↗
44. Filter-based deep-compression with global average pooling for convolutional networks10.1016/j.sysarc.2019.02.008 ↗
45. Global learnable pooling with enhancing distinctive feature for image classification10.1109/ACCESS.2020.2997078 ↗
46. Gradient amplification: An efficient way to train deep neural networks10.26599/BDMA.2020.9020004 ↗
47. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
48. Limited Data Rolling Bearing Fault Diagnosis with Few–Shot Learning10.1109/ACCESS.2019.2934233 ↗