Transformer Fault Diagnosis Based on BOA Optimized SVM
DOI: https://doi.org/10.62517/jbdc.202401415
Author(s)
Xiaopeng Zhang*, Yuan Chai
Affiliation(s)
Inner Mongolia Power (Group) Co., Ltd, Hohhot Power Supply Branch, Hohhot 010000, Inner Mongolia, China
*Corresponding Author.
Abstract
To improve the classification accuracy of transformers in different operating states, a BOA-SVM classification method for transformers in different operating states is proposed. Due to the excellent global search capability of the BOA method, in order to address the issue of the significant impact of key parameters on transformer operation status classification results in the SVM method, BOA is used to determine the key parameters of the SVM method, and the BOA-SVM model is applied to transformer operation status classification. In the end, the BOA-SVM fault diagnosis model has higher classification accuracy compared to using only the SVM model, with an average classification accuracy of 95.9%, and can effectively diagnose and classify the operating status of transformers.
Keywords
Butterfly Optimization Algorithm; SVM; Transformer; Fault Diagnosis; Parameter Optimization
References
[1]Yan P, Wang J B, Wang Y W Z. Transformer fault diagnosis based on MPA-RF algorithm and LIF technology. Measurement Science & Technology, 2024, 35(2):025504. 1-025504.10.
[2]Bai X, Zang Y, Li J, et al. Transformer fault diagnosis method based on two-dimensional cloud model under the condition of defective data. Electrical Engineering, 2024, 106(1). DOI:10. 1007/s00202-023-01964-7.
[3]Wang L Z, Chi J F, Ding Y Q, et al. Transformer fault diagnosis method based on SMOTE and NGO-GBDT. Scientific Reports, 2024, 14(1). DOI:10. 1038/s41598-024-57509-w.
[4]Lu W, Shi C, Fu H, et al. Research on transformer fault diagnosis based on ISOMAP and IChOA‐LSSVM. IET Electric Power Applications, 2023. DOI:10. 1049/elp2.12302.
[5]Liu J, Cai B, Yan S, et al. Transformer fault diagnosis based on the improved QPSO and random forest. IOP Publishing Ltd, 2024. DOI:10. 1088/ 1361-6501/ ad574c.
[6]Rao S, Yang S, Tucci M B S. Convolutional neural networks applied to dissolved gas analysis for power transformers condition monitoring. International journal of applied electromagnetics and mechanics, 2023, 73(4): 265-281.
[7]Kaur K, Bhalla D, Singh J. Fault Diagnosis for Oil Immersed Transformer Using Certainty Factor. IEEE transactions on dielectrics and electrical insulation: A publication of the IEEE Dielectrics and Electrical Insulation Society, 2024(1):31. DOI:10. 1109/TDEI.2023.3307513.
[8]Jin Y, Wu H, Zheng J, et al. Power Transformer Fault Diagnosis Based on Improved BP Neural Network. Electronics (2079-9292), 2023, 12(16). DOI:10. 3390/ electronics12163526.
[9]Mudholkar R R, Sawant S R, Tengshe G G, et al. Fuzzy Logic Transformer Design Algorithm (FLTDA). Active and Passive Electronic Components, 1999, 22(1):17-29. DOI:10.1155/1999/53850.
[10]Wang Y, Lu F, Li H. Synthetic Fault Diagnosis Method of Power Transformer Based on Rough Set Theory and Bayesian Network. Springer, Berlin, Heidelberg, 2008. DOI:10. 1007/ 978-3-540-87734-9_ 57.
[11]Xin-Gang C, Tai-Fu L I. Research on Expert System of Transformer Insulation Fault Diagnosis Based on DGA Characteristic Parameters. Transformer, 2005.
[12]Zhao Z, Guo Y, Xu A, et al. Fault diagnosis of the transformer based on QPSO-SVM. Journal of Physics: Conference Series, 2023, 2530(1). DOI:10. 1088/1742-6596/2530/1/012026.
[13]Li Y, Bao D, Luo C, et al. An Intelligent Fault Diagnosis Method for Oil-Immersed Power Transformer Based on Adaptive Genetic Algorithm. Springer Berlin Heidelberg, 2012. DOI:10.1007/978-3-642-25553-3_21.
[14] Duan H B, Xu C F, Xing Z H. A hybrid artificial bee colony optimization and quantum evolutionary algorithm for continuous optimization problems. International Journal of Neural Systems, 2010, 20(01):39-50. DOI:10. 1142/ S012906571000222X.
[15] Zhang J, Ding Y, Zhang X, et al. A Novel Method Based on Particle Swarm Optimization Support Vector Neural Network for Transformer Fault Diagnosis// International Symposium on Neural Networks.Springer, Singapore, 2024. DOI:10. 1007/978-981-97-4399-5_51.
[16] S. S, G. K. R. Copy-Move Forgery Detection and Classification Using Improved Butterfly Optimization Algorithm-based Convolutional Neural Network. International Journal of Intelligent Engineering & Systems, 2024, 17(1). DOI:10. 22266/ ijies2024. 0229. 72.
[17] Arora S, Singh S, Yetilmezsoy K. A modified butterfly optimization algorithm for mechanical design optimization problems. Journal of the Brazilian Society of Mechanical Sciences & Engineering, 2018, 40(1):21. DOI:10. 1007/ s40430-017-0927-1.
