Dynamically enhanced weighted network acoustic and photoelectric GIS fault diagnosis based on attention mechanism
1
State Grid Jiangsu Electric Power Co., Ltd. Electric Power Science Research Institute, Nanjing 211100, China
2
Xinjiang Electric Power Research Institute, State Grid Corporation of China, Urumqi 830000, China
3
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Submission date: 2024-12-31
Final revision date: 2025-02-18
Acceptance date: 2025-04-29
Online publication date: 2025-06-19
Publication date: 2025-06-19
KEYWORDS
fault diagnosisPower transformerPhotoacoustic spectroscopyDomain adaptive intermediate class distribution alignment networkAdaSoftmax
TOPICS
ABSTRACT
In power systems, the normal functioning of gas-insulated switchgear (GIS) is essential for the security of the electrical grid. However, when a single signal is used for discharge detection and diagnosis, it will be interfered. Through joint analysis of different signals, fault diagnosis can be more accurately performed. To address this problem, this paper proposes a dynamically enhanced weighted network model (AMB-DEWNM) based on the attention mechanism. The model first extracts fault features from the PRPD spectra of UHF, optical and ultrasonic signals through a multi-scale convolutional neural grid. A two-tier focus module is introduced to enhance fault characteristics that are insensitive to changes in operating conditions. A new dynamic enhanced weighted voting strategy (DEWVS) is designed. This strategy constructs a diagnostic performance index matrix by considering the diagnostic accuracy and misclassification rate of the base model to dynamically adjust the voting weight of each base model. distribution to obtain more reliable collaborative diagnostic results. Test outcomes demonstrate that the error detection precision of the AMB-DEWNM system is notably enhanced. Compared with other advanced network models, the diagnosis accuracy is as high as 95.28%. It has high stability and robustness, and provides fault detection and maintenance for GIS. strong support.
FUNDING
This study was supported by Project Supported by the Science and Technology Project of State Grid Corporation of China (5500-202218132A-1-1-ZN).
REFERENCES (26)
1.
Wang YX, Yan J, Wang JH, Geng YS. A small-sample GIS partial discharge diagnosis method based on multi-level second-order attention twin networks, Transac. China Electrotech. Soc. 2023;38(8):2255-2264.
2.
Hu ZY, Geng QY, Wei L, Chang YN, Li QM. The synergistic suppression effect and optimization design method of driving electrodes and particle traps in DC GIS/GIL, Transac. China Electrotech. Soc. 2023;38(12):3338-3349.
3.
Du ZY, Hao ZY, Zhao PF, Wang H, Hao Q. Research on the propagation characteristics of ultrasonic guided waves in gas-insulated transmission lines suitable for sound source localization, Transac. China Electrotech. Soc. 2024;39(3):852-862.
4.
Li Z, Wang H, Qian Y, Huang R, Cui QH. Noise-robust partial discharge pattern recognition based on accelerated robust features, Transac. China Electrotech. Soc. 2022;37(3):775-785.
5.
Qu JL, Yu L, Yuan T, Tian YP, Gao F. An adaptive fault diagnosis algorithm for rolling bearings based on one-dimensional convolutional neural networks, Chinese J. Sci. Instrument. 2018;39(7):134-143. https://doi.org/10.19650/j.cnk....
6.
Ohenhen PE, Nwaobia NK, Nwasike CN, Gidiagba JO, Zni EC. Diagnostics and monitoring in electro-mechanical assemblies: assessing the latest tools and techniques for system health prediction. Acta Electron. Malays. 2024;8(1):11-20. https://doi.org/10.26480/aem.0....
7.
Zhou X, Wu XT, Tian T, Bai J, Zhang ZY, Li JH. Condition assessment method of GIS disconnector based on vibration-thermal-electrical multi-parameter signal characteristics, Electric Power Engineering Technology. 2024;43(1):220-228.
8.
Liao JM, Guan XY, Lin JG, Liu J, Zhao JY. GIS vibration signal denoising and mechanical defect identification based on CycleGAN and CNN. Electric Power Engineering Technology. 2023;42(5):37-45. https://doi.org/10.12158/j.209....
9.
Shi Z, Chen J, Zi Y, Chen Z. DecouplingNet: A stable knowledge distillation decoupling net for fault detection of rotating machines under varying speeds. IEEE Trans. Neural Netw. Learn. Syst. 2024;35(8): 11276-11290. https://doi.org/10.1109/TNNLS.....
10.
Qian Q, Qin Y, Luo J, Wang Y, Wu F. Deep discriminative transfer learning network for cross-machine fault diagnosis. Mech. Syst. Signal Process. 2023;186:109884. https://doi.org/10.1016/j.ymss....
11.
Qian Q, Zhou J, Qin Y. Relationship transfer domain generalization network for rotating machinery fault diagnosis under different working conditions. IEEE Trans. Industr. Inform. 2023;19(1):9898-9908. https://doi.org/10.1109/TII.20....
12.
Feng Y, Chen J, He S, Pan T, Zhou Z. Globally localized multisource domain adaptation for cross-domain fault diagnosis with category shift. IEEE Trans. Neural Netw. Learn. Syst. 2023;34(6):3082-3096. https://doi.org/10.1109/TNNLS.....
13.
Wen L, Gao L, Li X. A new deep transfer learning based on sparse auto-encoder for fault diagnosis. IEEE Trans. Syst., Man, Cybern., Syst. 2019;49(1):136-144. https://doi.org/10.1109/TSMC.2....
14.
Zhu J, Huang CG, Shen C, Shen Y. Cross-domain open-set machinery fault diagnosis based on adversarial network with multiple auxiliary classiffers. IEEE Trans. Ind. Informat. 2022;18(1):8077-8086. tps://doi.org/10.1109/TII.2021.3138558.
15.
Jiao J, Zhao M, Lin J. Multi-weight domain adversarial network for partial-set transfer diagnosis. IEEE Trans. Ind. Electron. 2022;69(4):4275-4284. https://doi.org/10.1109/TIE.20....
16.
Cao Z, Long M, Wang L, Jordan MI. Partial transfer learning with selective adversarial networks. in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. 2018:2724-2732.
17.
Li W, Chen Z, He G. A novel weighted adversarial transfer network for partial domain fault diagnosis of machinery. IEEE Trans. Ind. Informat. 2021;17(3): 1753-1762. https://doi.org/10.1109/TII.20....
18.
Xia Y, Shen C, Wang D, Shen Y, Huang W, Zhu Z. Moment matching-based intraclass multisource domain adaptation network for bearing fault diagnosis. Mech. Syst. Signal Process. 2022;168:108697. https://doi.org/10.1016/j.ymss....
19.
Chai Z, Zhao C, Huang B. Multisource-reffned transfer network for industrial fault diagnosis under domain and category inconsistencies. IEEE Trans. Cybern. 2022;52(9):9784-9796. https://doi.org/10.1109/TCYB.2....
20.
Deng M, Deng A, Shi Y, Xu M. Correlation regularized conditional adversarial adaptation for multi-target-domain fault diagnosis. IEEE Trans. Ind. Informat. 2022;18(12):8692-8702. https://doi.org/10.1109/TII.20....
21.
Li J, Wang Y, Zi Y, Zhang Z. Whitening-net: A generalized network to diagnose the faults among different machines and conditions. IEEE Trans. Neural Netw. Learn. Syst. 2022;33(1):5845-5858. https://doi.org/10.1109/TNNLS.....
22.
Bacha K, Souahlia S, Gossa M. Power transformer fault diagnosis based on dissolved gas analysis by support vector machine. Electric Power Syst. Res. 2012;83(1):73-79. https://doi.org/10.1016/j.epsr....
23.
Liu W, Wen Y, Yu Z, Li M, Raj B, Song L. SphereFace: Deep hypersphere embedding for face recognition. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 2017:212-220.
24.
Wang H. CosFace: Large margin cosine loss for deep face recognition. in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. 2018:5265-5274.
25.
Rosenberg A, Hirschberg J. V-measure: A conditional entropybased external cluster evaluation measure. in Proc. Joint Conf. Empirical Methods Natural Lang. Process. Comput. Natural Lang. Learn. (EMNLP-CoNLL). 2007:410-420. https://doi.org/10.7916/D80V8N....
26.
Hardoon DR, Szedmak S, Shawe-Taylor J. Canonical correlation analysis: An overview with application to learning methods. Neural Comput. 2024;16(12): 2639-2664. https://doi.org/10.1162/089976....
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.
