Research on Identification Method of Transformer Windings’ Loose Vibration Spectrum Considering a Multi-Load Current Condition
Source abstract
Abstract
During transformer operation, long-term vibration causes the winding to loosen axially. When hit by a short-circuit, the winding deforms to different extents. Thus, identifying early looseness faults in transformer windings is vital for power systems’ stability. To address issues including scarce vibration data across multiple load conditions for transformer winding looseness faults, inadequate extraction of two-dimensional spectrogram features, and the inability to boost recognition accuracy caused by overfitting during fault recognition model training, this study constructed a 10 kV power transformer vibration test platform. It measured the vibration signals on the box surface under various winding looseness conditions and built a time–frequency-domain vibration spectrum library for different load currents. Then, a fault identification model based on vibration spectra and ConvNeXt was constructed, and model verification and analysis were carried out. The results indicate that after training, the fault recognition accuracy of the spectrum containing three load conditions is comparable to that of a single load condition. The average recognition accuracy at six box-surface measuring points reaches 97.9%. Moreover, the ConvNeXt model outperforms the traditional ResNet50 by 1.2%. This new model effectively addresses overfitting and offers strong technical support for detecting different transformer winding looseness faults.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Power Transformer Diagnostics and Insulation · High voltage insulation and dielectric phenomena · Machine Fault Diagnosis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University, Chongqing 400044, China
Ultra-High Voltage Branch of State Grid Chongqing Electric Power Company, Chongqing 400050, China
Funding
State Grid Chongqing Electric Power Company Technology Project
References (40)
Show source-provided references
1. Diagnosis Method of Transformer Winding Mechanical State Based on Current-Frequency-Vibration Parameter
2. Spatially Continuous Transformer Online Temperature Monitoring Based on Distributed Optical Fibre Sensing Technology10.1049/hve2.12031 ↗
3. State Diagnosis Method of Transformer Winding Deformation Based on Fusing Vibration and Reactance Parameters10.1049/iet-epa.2019.0564 ↗
4. A Study of the Sweep Frequency Impedance Method and Its Application in the Detection of Internal Winding Short Circuit Faults in Power Transformers10.1109/TDEI.2015.004977 ↗
5. Innovative Diagnosis of Transformer Winding Defects Using Fuzzy and Neutrosophic Cross Entropy Measures10.1016/j.aei.2025.103196 ↗
6. (2015). Transformer Reliability Survey, CIGRE. CIGRE Working Group A2.37.
7. Ribeiro, C.d.J., Marques, A.P., Bezerra Azevedo, C.H., Poli Souza, D.C., Alvarenga, B.P., and Nogueira, R.G. (June, January 31). Faults and Defects in Power Transformers—A Case Study. Proceedings of the 2009 IEEE Electrical Insulation Conference, Montreal, QC, Canada.10.1109/EIC.2009.5166333 ↗
8. Application of Vibration Analysis in Transformer Fault Diagnosis and Hidden Peril Management
9. Research Progress on Oil-Immersed Transformer Mechanical Condition Identification Based on Vibration Signals10.1016/j.rser.2024.114327 ↗
10. Research on Mechanical Fault Diagnosis Method of Power Transformer Winding
11. Granados-Lieberman, D., Huerta-Rosales, J.R., Gonzalez-Cordoba, J.L., Amezquita-Sanchez, J.P., Valtierra-Rodriguez, M., Camarena-Martinez, D., and Darmon, M. (2023). Time-Frequency Analysis and Neural Networks for Detecting Short-Circuited Turns in Transformers in Both Transient and Steady-State Regimes Using Vibration Signals. Appl. Sci., 13.10.3390/app132212218 ↗
12. Short-Time Fourier Transform: Two Fundamental Properties and an Optimal Implementation10.1109/TSP.2003.810293 ↗
13. Huerta-Rosales, J.R., Granados-Lieberman, D., Garcia-Perez, A., Camarena-Martinez, D., Amezquita-Sanchez, J.P., and Valtierra-Rodriguez, M. (2021). Short-Circuited Turn Fault Diagnosis in Transformers by Using Vibration Signals, Statistical Time Features, and Support Vector Machines on FPGA. Sensors, 21.10.3390/s21113598 ↗
14. Support Vector Machines10.1109/5254.708428 ↗
15. Vibration Signal-Based Fusion Residual Attention Model for Power Transformer Fault Diagnosis10.1109/JSEN.2024.3382811 ↗
16. Research on Digital Technology of Mechanical Structure Fault Diagnosis of Power Transformer Based on Comprehensive Feature Extraction and SABO-PNN10.1109/TASC.2024.3442980 ↗
17. Interpretable Analysis of Transformer Winding Vibration Characteristics: SHAP and Multi-Classification Feature Optimization10.1016/j.ijepes.2025.110585 ↗
18. Load Frequency Control in Power Systems by a Robust Backstepping Sliding Mode Controller Design10.1016/j.egyr.2023.08.008 ↗
19. Machine Learning Based Multi-Method Interpretation to Enhance Dissolved Gas Analysis for Power Transformer Fault Diagnosis10.1016/j.heliyon.2024.e25975 ↗
20. Zhang, L., Xu, Z., Qiao, T., Lu, C., Su, H., and Luo, Y. (2024, January 26). Transformer Fault Diagnosis Based on Adversarial Generative Networks and Deep Stacked Autoencoder. Proceedings of the 2024 7th International Conference on Energy, Electrical and Power Engineering (CEEPE), Yangzhou, China.10.1109/CEEPE62022.2024.10586464 ↗
21. Karen, S., Andrea, V., and Andrew, Z. (2013, January 2–4). Deep inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. Proceedings of the 2nd International Conference on Learning Representations; International Conference on Learning Representations, Banff, AB, Canada.
22. Parkash, C., and Abbasi, A.R. (2023). Transformer’s Frequency Response Analysis Results Interpretation Using a Novel Cross Entropy Based Methodology. Sci. Rep., 13.10.1038/s41598-023-33606-0 ↗
23. Digital Twin-Assisted Interpretable Transfer Learning: A Novel Wavelet-Based Framework for Intelligent Fault Diagnostics from Simulated Domain to Real Industrial Domain10.1016/j.aei.2024.102681 ↗
24. Transformer Winding Looseness Fault Diagnosis Model Based on GAF and Depth Residual Network
25. A Fault Diagnosis Method for Transformer Winding Looseness Based on Gramian Angular Field and Transfer Learning-AlexNet
26. Ji, S., Jia, Y., Huang, X., Yang, X., and Zhang, F. (2024). Vibration characteristics and loosening fault detection method of transformer bushing turret area. Eng. Mech., 12.
27. Characteristics and Influence Factors of Winding Axial Vibration of Power Transformer inSteady-State Operation Condition
28. A Deep Learning Framework for Time Series Classification Using Relative Position Matrix and Convolutional Neural Network10.1016/j.neucom.2019.06.032 ↗
29. Bearing Fault Diagnosis with Varying Conditions Using Angular Domain Resampling Technology, SDP and DCNN10.1016/j.measurement.2020.107616 ↗
30. Liu, Z., Zhang, H., Lv, Z., Jia, H., Liang, X., and Wang, Q. (2024). Identification of Composite Power Quality Disturbances Based on Relative Position Matrix. Front. Energy Res., 11.10.3389/fenrg.2023.1326522 ↗
31. Wang, Z., and Oates, T. (2015, January 25–31). Imaging Time-Series to Improve Classification and Imputation. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), Buenos Aires, Argentina.
32. Research on Multi-Level Feature Extraction Model of Converter Transformer Vibration Signal
33. Analysis of Transformer Fault Characteristics Based on Vibration Signal
34. 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 ↗
35. Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18–24). A ConvNet for the 2020s. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01167 ↗
36. Lee, G.T., and Kwon, O.-R. (2024). A Predictive Model Based on Transformer with Statistical Feature Embedding in Manufacturing Sensor Dataset. arXiv.
37. Zhang, C., Qin, F., Zhao, W., Li, J., and Liu, T. (2023). Research on Rolling Bearing Fault Diagnosis Based on Digital Twin Data and Improved ConvNext. Sensors, 23.10.3390/s23115334 ↗
38. Hendrycks, D., and Gimpel, K. (2023). Gaussian Error Linear Units (GELUs). arXiv.
39. Loshchilov, I., and Hutter, F. (2019). Decoupled Weight Decay Regularization. arXiv.
40. T-viSNE: Interactive Assessment and Interpretation of t-SNE Projections10.1109/TVCG.2020.2986996 ↗