Transformer Fault Diagnosis Method Based on ZOA-Optimized SVM

DOI: https://doi.org/10.62517/jbdc.202501219

Author(s)

Xiangnan Zhu*

Affiliation(s)

Hohhot Power Supply Branch, Inner Mongolia Power (Group) Co., Ltd., Hohhot, Inner Mongolia, China * Corresponding Author

Abstract

To address the issues of difficulty in extracting effective features and the significant impact of model key parameters on fault classification accuracy when using Support Vector Machine (SVM) for transformer fault diagnosis, this paper proposes a transformer fault diagnosis method that combines feature extraction and Zebra Optimization Algorithm (ZOA) to optimize SVM. Firstly, Principal Component Analysis (PCA) is used to extract the features of the input variables, reducing the dimensionality of the feature variables and weakening the correlation between variables. To solve the problem that the SVM model is greatly affected by parameter settings in the transformer fault classification process, ZOA is proposed to optimize it, determine its key parameters, and establish the ZOA-SVM model. The feature vectors processed by PCA for dimensionality reduction are divided into training and test sets. The test set samples are used to train the ZOA-SVM model, and the test set data is input into the trained ZOA-SVM model for fault classification. Experimental results show that compared with other common methods such as Cuckoo Search Algorithm and Firefly Algorithm, the transformer fault diagnosis model based on ZOA-optimized SVM has higher fault classification accuracy, with an overall fault diagnosis accuracy rate of 98.33%.

Keywords

SVM; ZOA; PCA; Transformer; Fault Diagnosis

References

[1] Zhang S, Zhou H .Transformer Fault Diagnosis Based on Multi-Strategy Enhanced Dung Beetle Algorithm and Optimized SVM. Energies, 2024, 17(24): 6296-6296. [2] Zhang X, Chai Y. Transformer Fault Diagnosis Based on BOA Optimized SVM. Journal of Big Data and Computing, 2024, 2(4). [3] Liu X, Wang H, Gao Z, et al. Research on fault localization of distribution transformers based on frequency response analysis and support vector machine (SVM). Frontiers in Energy Research, 2024, 121477556-1477556. [4] DingC, YuD ,LiuX , et al. Research on Transformer Fault Diagnosis by WOA‐SVM Based on Feature Selection and Data Balancing. IEEJ Transactions on Electrical and Electronic Engineering, 2024, 20(1): 41-49. [5] Qin H , Jiaqing M , Saisai R , et al. Fault Diagnosis of Oil‐Immersed Power Transformers Using SVM and Logarithmic Arctangent Transform. IEEJ Transactions on Electrical and Electronic Engineering, 2022, 17(11): 1562-1569. [6] Zahra K, Farshid N , Mehran Y , et al. An EKF‐SVM machine learning‐based approach for fault detection and classification in three‐phase power transformers. IET Science, Measurement & Technology, 2021, 15(2): 130-142. [7] Prasad S E ,Sonia E S ,Suresh N K , et al. Active and Reactive Power Control in Three-Phase Grid-Connected Electric Vehicles using Zebra Optimization Algorithm and Multimodal Adaptive Spatio-Temporal Graph Neural Network. Renewable Energy Focus, 2025, 54100715-100715. [8] Hou L , Huang Q . A smart WSNs node with sensor computing and unsupervised One-Class SVM classifier for machine fault detection. Measurement, 2025, 242(PB): 115843-115843. [9] Ma J ,Liu X ,Hu J , et al. Stator ITSC Fault Diagnosis of EMU Asynchronous Traction Motor Based on apFFT Time-Shift Phase Difference Spectrum Correction and SVM. Energies, 2023, 16(15). [10] Junbo Z , Maohua X ,Yue N , et al. Rolling Bearing Fault Diagnosis Based on WGWOA-VMD-SVM. Sensors, 2022, 22(16): 6281-6281.