Fault pattern recognition and prediction of transformer voicing based on neural network
1
Electric Power Research Institute of Jilin Electric Power Co., Ltd., Changchun 130012, Jilin, China
2
State Grid Jilin Electric Power Co., Ltd., Changchun 130022, Jilin, China
3
State Grid Jilin Electric Power Co., Ltd. Ultra-High Voltage Company, Changchun 132000, Jilin, China
Submission date: 2024-11-22
Final revision date: 2025-08-28
Acceptance date: 2025-09-05
Online publication date: 2025-09-11
Publication date: 2025-09-11
Corresponding author
Jieyuan Chen
Electric Power Research Institute of Jilin Electric Power Co., Ltd., Changchun 130012, Jilin
Electric Power Research Institute of Jilin Electric Power Co., Ltd., Changchun 130012, Jilin
Diagnostyka 2025;26(3):2025315
KEYWORDS
TOPICS
ABSTRACT
With the complexity of power system, transformer fault detection and early warning face challenges. Traditional methods fail to identify potential failures, leading to increased risk of equipment damage and power outages. In this study, an efficient fault recognition and prediction model based on voice print signal was developed by combining convolution neural network and long and short term memory network. After training and verification, the accuracy rate of the model's recognition of common fault modes reached 95.1%. In the complex fault mode, although the recognition rate has decreased, the whole early warning system still has high reliability and practicability. The research results provide technical support for the intelligent maintenance of transformers, and help to improve the safety and stability of power system.
FUNDING
This research received no external funding.
REFERENCES (22)
1.
Li M, Zhan HM, Qiu AN. Voiceprint recognition of transformer fault based on blind source separation and Convolution neural network. In: 2021 IEEE Electrical Insulation Conference (EIC). IEEE; 2021:618-621. https://doi.org/10.1109/EIC498....
2.
Yu ZT, Li DJ, Chen LY, Yan HJ. The research on transformer fault diagnosis method based on vibration and noise voiceprint imaging technology. In: Proceedings of the 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA 2019). 2019:216-221. https://doi.org/10.1109/iciea.....
3.
Shan SJ, Liu JB, Wu SG, Shao Y, Li HP. A motor bearing fault voiceprint recognition method based on Mel-CNN model. Measurement. 2023;207:112408. https://doi.org/10.1016/j.meas....
4.
Wan ST, Dong F, Zhang X, Wu WB, Li JL. Fault voiceprint signal diagnosis method of power transformer based on mixup data enhancement. Sensors. 2023;23(6):3341. https://doi.org/10.3390/s23063....
5.
Jiang Y, Sun HW, Hong LZ, Lin R, Yan W, Li Z. Research on voiceprint recognition of electrical faults with lower false alarm rate. In: 2021 Power System and Green Energy Conference (PSGEC). IEEE; 2021:599-603. https://doi.org/10.1109/PSGEC5....
6.
Ma ZP, Zhao M, Ou SD, Ma B, Zhang Y. Physics-inspired sparse voiceprint sensing for bearing fault diagnosis. IEEE Trans Ind Inform. 2024;20(9):11273-11284. https://doi.org/10.1109/TII.20....
7.
Li H, Yao Q, Li X. Voiceprint fault diagnosis of converter transformer under load influence based on multi-strategy improved mel-frequency spectrum coefficient and temporal Convolution network. Sensors. 2024;24(3):757. https://doi.org/10.3390/s24030....
8.
Jiang WL, Li ZB, Li JJ, Zhu Y, Zhang PY. Study on a fault identification method of the hydraulic pump based on a combination of voiceprint characteristics and extreme learning machine. Processes. 2019;7(12):894. https://doi.org/10.3390/pr7120....
9.
Yu ZR, Wei YJ, Niu B, Zhang XL. Automatic condition monitoring and fault diagnosis system for power transformers based on voiceprint recognition. IEEE Trans Instrum Meas. 2024;73: 9600411. https://doi.org/10.1109/TIM.20....
10.
Wang SH, Zhou YR, Ma ZX. Research on fault identification of high-voltage circuit breakers with characteristics of voiceprint information. Sci Rep. 2024;14(1):9340. https://doi.org/10.1038/s41598....
11.
Abulizi J, Chen Z, Liu P, Sun HW, Ji CW, Li Z. Research on voiceprint recognition of power transformer anomalies using gated recurrent unit. In: 2021 Power System and Green Energy Conference (PSGEC). IEEE; 2021:743-747. https://doi.org/10.1109/PSGEC5....
12.
Dong YQ, Wang DL, Pan Y, Di J, Chen AR. Fault detection of in-service bridge expansion joint based on voiceprint recognition. Struct Control Health Monit. 2024:270912. https://doi.org/10.1155/2024/1....
13.
Wang JX, Zhao ZS, Zhu J, Li X, Dong F, Wan ST. Improved support vector machine for voiceprint diagnosis of typical faults in power transformers. Machines. 2023;11(5):539. https://doi.org/10.3390/machin....
14.
Zhang PY, Jiang WL, Zheng YF, Zhang SQ, Zhang S, Liu SY. Hydraulic-pump fault-diagnosis method based on mean spectrogram bar graph of voiceprint and ResNet-50 model transfer. J Mar Sci Eng. 2023;11(9):1678. https://doi.org/10.3390/jmse11....
15.
Xiang S, Fei X, Long X, Jidong C. Research on transformer voiceprint feature extraction oriented to complex noise environment. Int J Acoust Vib. 2023;28(2):193-199. https://doi.org/10.20855/ijav.....
16.
Chen L, Wang RH, Hu F, Li Z, Liang L, Lei CH. Research on voice print recognition of electrical faults based on attention-MFCC algorithm. In: 2021 Power System and Green Energy Conference (PSGEC). IEEE; 2021:748-751. https://doi.org/10.1109/PSGEC5....
17.
Zhou YR, Ma ZX, Chen H, Wang RH. Analysis of multiple-faults of high-voltage circuit breakers based on non-negative matrix decomposition. Glob Energy Interconnect. 2024;7(2):179-189. https://doi.org/10.1016/j.gloe....
18.
Gong CSA, Su CHS, Liu YE, Guu DY, Chen YH. Deep learning with LPC and wavelet algorithms for driving fault diagnosis. Sensors. 2022;22(18):7072. https://doi.org/10.3390/s22187....
19.
Zhou HL, Lu L, Shen MW, Su ZT, Huang YX. An efficient noise reduction method for power transformer voiceprint detection based on poly-phase filtering and complex variational modal decomposition. Electronics. 2024;13(2):338. https://doi.org/10.3390/electr....
20.
Pei XP, Han ST, Bao YY, Chen W, Li HJ. Fault diagnosis of transformer winding short circuit based on WKPCA-WM and IPOA-CNN. Front Energy Res. 2023;11:1151612. https://doi.org/10.3389/fenrg.....
21.
Han S, Wang BW, Liao SZ, Gao F, Chen M. Defect identification method for transformer end pad falling based on acoustic stability feature analysis. Sensors. 2023;23(6):3258. https://doi.org/10.3390/s23063....
22.
Zhang GZ, Chen K, Zhang XX. Audible acoustic characteristics of epoxy resins with partial discharge. Front Energy Res. 2022;10:1006834. https://doi.org/10.3389/fenrg.....
Share
RELATED ARTICLE
| eISSN: | 2449-5220 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
