High-voltage circuit breaker fault voiceprint recognition based on prototype similar domain adaptive spectral morphological neural network

• Autorzy: Wang Dong , Zhou Lubo , Xie Liyun , Liu Xipu , Dong Shiqi , Liu Junhua

Identyfikatory

DOI

10.29354/diag/206079

• Języki publikacji: EN

Abstrakty

EN

High-voltage circuit breakers will emit continuous vibration signals during operation. The signals contain a large number of pulses and fluctuations caused by faults. They are the main data source for evaluating the functioning condition for high-tension breaker switches. To aim for examine its vocal features in vibration acoustic signals of high-tension breaker switches in different operating states, a prototype similarity domain adaptive spectral morphological neural network (PSDA-SMNN) was proposed. First, the vibration signal is denoised using spectral morphology variational mode decomposition combined with fast singular value decomposition method. Secondly, the labeled data of a certain operational state serves utilized for this information origin area, while this untagged information from different operational states serves utilized for this training objective area, and the prototype network distance similarity is used to align the feature distribution between the domains; then, meta-training is used to the domain network undergoes internal supervised training, and the network in the target domain undergoes external unsupervised training using the virtual label backpropagation algorithm. Through internal and external loop training, the difference in feature distribution between domains is reduced, and unlabeled faults of high-tension breaker switches in varying operational states are recognized. Test outcomes indicate which the suggested framework is able to precisely identify the malfunction operational condition for high-tension breaker switches and detect common issues for high-tension breaker switches under various interference settings, having a classification precision of approximately 95%.

Słowa kluczowe

EN

high-voltage circuit breaker; voiceprint recognition; prototype similarity domain; deep transfer learning; spectral morphology variational mode decomposition

• Wydawca: Polskie Towarzystwo Diagnostyki Technicznej
• Czasopismo: Diagnostyka
• Rocznik: 2025
• Tom: Vol. 26, No. 3
• Strony: art. no. 2025301
• Opis fizyczny: Bibliogr. 24 poz., rys.

Twórcy

autor

Wang Dong

• State Grid Shanghai Ultra High Voltage Company, Shanghai 200122, China

• https://orcid.org/0009-0000-4348-7718

autor

Zhou Lubo

• State Grid Shanghai Ultra High Voltage Company, Shanghai 200122, China

• https://orcid.org/0009-0004-2508-4092

autor

Xie Liyun

• State Grid Shanghai Ultra High Voltage Company, Shanghai 200122, China

• https://orcid.org/0009-0009-9254-4091

autor

Liu Xipu

• State Grid Shanghai Ultra High Voltage Company, Shanghai 200122, China

• https://orcid.org/0009-0001-5603-9970

autor

Dong Shiqi

• State Grid Shanghai Ultra High Voltage Company, Shanghai 200122, China

• https://orcid.org/0009-0009-0447-6560

autor

Liu Junhua

• State Grid Shanghai Ultra High Voltage Company, Shanghai 200122, China

• https://orcid.org/0009-0003-4808-9665

Bibliografia

• 1. Zang CY, Zeng J, Li P, et al. Intelligent diagnosis model of mechanical fault for power transformer based on SVM algorithm. High Voltage Apparatus (China) 2023; 59(12): 216-222-229. https://doi.org/10.1109/ICSRS.2018.8688719.
• 2. Shao Y, Wu JW, Ma SL, et al. Integrated SVM method with AM-ReliefF feature selection for mechanical fault diagnosis of high voltage circuit breakers. Proceedings of the CSEE (China) 2021; 41(08): 2890-2901.
• 3. Wan ST, Ma XD, Chen L, et al. State evaluation and fault diagnosis of high-voltage circuit breaker based on short-time energy entropy ratio of vibration signal and DTW. High Voltage Engineering (China) 2020; 46(12): 4249-4257.
• 4. Wang S, Zhou Y, & Ma Z. Research on fault identification of high-voltage circuit breakers with characteristics of voiceprint information. Sci Rep. 2024; 14: 9340. https://doi.org/10.1038/s41598-024-59999-0.
• 5. Chen H, Han C, Zhang Y, et al. Investigation on the fault monitoring of high-voltage circuit breaker using improved deep learning. PLOS ONE 2023; 18(12):e0295278. https://doi.org/10.1371/journal.pone.0295278.
• 6. Ye XY, Yan J, Wang YX, et al. A novel capsule convolutional neural network with attention mechanism for high-voltage circuit breaker fault diagnosis. Electric Power Systems Research 2022; 209:108003. https://doi.org/10.1016/j.epsr.2022.108003.
• 7. Ye X, Yan J, Wang Y, et al. A novel U-Net and capsule network for few-shot high-voltage circuit breaker mechanical fault diagnosis. Measurement, 2022;199:111527. https://doi.org/10.1016 /j.measurement.2022.111527.
• 8. Zhang D, Wang Y, Li Z, et al. Analysis of prebreakdown arcing time in vacuum circuit breakers based on empirical wavelet transform. Transactions of China Electrotechnical Society 2024; 1-12.
• 9. Chen H, Li Z, Zhang S, et al. Short-term transformer error prediction based on MHA-CNN-SLSTM and error compensation. Power System Protection and Control 2024; 52(24), 74-84.
• 10. Ruan J, Wang X, Zhou T, et al. Fault identification of high voltage circuit breaker trip mechanism based on PSR and SVM. IET Generation, Transmission & Distribution. 2023;17(6):1179-1189. https://doi.org/10.1049/gtd2.12725.
• 11. Yang Q, Liao Y, Li J, et al. Cross-domain zero-shot learning for enhanced fault diagnosis in high-voltage circuit breakers. Neural Networks 2024; 180: 106681. https://doi.org/10.1016/j.neunet.2024.106681.
• 12. Li T, Xia Y, Pang X, et al. Mechanical fault diagnosis of high voltage circuit breaker using multimodal data fusion. PeerJ Computer Science 2024; 10: e2248. https://doi.org/10.7717/peerjcs.2248.
• 13. Yan J, Wang Y, Yang Z, et al. Few-shot mechanical fault diagnosis for a high-voltage circuit breaker via a transformer-convolutional neural network and metric meta-learning. In IEEE Transactions on Instrumentation and Measurement 2023; 72: 1-11. https://doi.org/10.1109/TIM.2023.3309387.
• 14. Moradzadeh A, Pourhossein K, Mohammadi-Ivatloo B, Mohammadi F. Locating inter-turn faults in transformer windings using isometric feature mapping of frequency response traces. IEEE Trans. Ind. Informat. 2021; 17(10): 6962-6970. https://doi.org/10.1109/TII.2020.3016966.
• 15. Zhao Y, Xu H, Tian Y, et al. Fault detection of distribution network photovoltaic inverters based on a fusion attention mechanism autoencoder. Smart Power 2024; 52(11): 1-7.
• 16. Chen Y, Duan W, He Y, et al. State of health estimation for batteries using denoising autoencoder and gated recurrent hybrid neural network. Transactions of China Electrotechnical Society 2024; 39(24): 7933-7949.
• 17. Luo G, Yang X, Shang B, et al. High-impedance ground fault detection in distribution networks based on an improved stacked denoising autoencoder. Power System Protection and Control 2024; 52(24): 149-160.
• 18. Wang J, Yan X, Ye Q, et al. Few-shot transfer learning with attention mechanism for high-voltage circuit breaker fault diagnosis. In IEEE Transactions on Industry Applications 2022; 58(3): 3353-336. https://doi.org/10.1109/TIA.2022.3159617.
• 19. Vu-Cong T, Dalstein M, Toigo C, Jacquier F, Girodet A. Partial discharge measurement in DC GIS: Comparison between conventional and UHF methods. in Proc. IEEE Conf. Electr. Insul. Dielectric Phenomena (CEIDP) 2021; 607-610. https://doi.org/10.1109/CEIDP50766.2021.9705420.
• 20. Chen L, Wan S, Dou L. Improving diagnostic performance of high-voltage circuit breakers on imbalanced data using an oversampling method. In IEEE Transactions on Power Delivery 2022; 37(4): 2704-2716. https://doi.org/10.1109/TPWRD.2021.3114547.
• 21. Qin Y, Qian Q, Wang Y, et al. Intermediate distribution alignment and its application into mechanical fault transfer diagnosis. IEEE Transactions on Industrial Informatics 2022; 18(10): 7305-7315. https://doi.org/10.1109/TII.2022.3149934.
• 22. Han T, Liu C, Yang WG, et al. Deep transfer network with joint distribution adaptation: A new intelligent fault diagnosis framework for industry application. ISA Transactions 2020; 97: 269-281. https://doi.org/10.1016/j.isatra.2019.08.012.
• 23. Xu H. A hybrid knowledge-based and data-driven method for aging-dependent reliability evaluation of high-voltage circuit breaker. In IEEE Transactions on Power Delivery 2023; 38(6): 4384-4396. https://doi.org/10.1109/TIE.2019.2953010.
• 24. Feng Y, Chen JL, Zhang TC, et al. Semi supervised meta-learning networks with squeeze-and excitation attention for few-shot fault diagnosis. ISA Transactions 2022; 120: 383-401. https://doi.org/10.1016/j.isatra.2021.03.013.