Transformer Fault Diagnosis Method Based on SSA-Optimized SVM

DOI: https://doi.org/10.62517/jes.202502211

Author(s)

Xiangnan Zhu*

Affiliation(s)

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

Abstract

Aiming at the problem of low accuracy in current transformer fault diagnosis methods, a transformer fault diagnosis method based on the Sparrow Search Algorithm (SSA) optimized Support Vector Machine (SVM) model is proposed. Firstly, the Kernel Principal Component Analysis (KPCA) method is used to process the high-dimensional data of transformer fault features to reduce the dimension and weaken the interference of data sparsity on the results. To address the issue that the kernel function parameters and penalty coefficients in SVM have a significant impact on the fault classification effect, it is proposed to use SSA to optimize the parameters of SVM to determine the best parameter combination and establish the SSA-SVM fault diagnosis model. The obtained data is divided into training and test sets. The training set is used to train the SSA-SVM fault diagnosis model, and the test set sample data is input into the trained model for fault diagnosis. To verify the effectiveness of this method, it is compared with several common fault diagnosis methods. The results show that the proposed fault diagnosis method has significantly higher fault recognition accuracy than other models, verifying its advanced nature.

Keywords

KPCA; SVM; SSA; Transformer; Fault Diagnosis

References

[1] Liang B ,Sun Z ,Yang Z , et al. Data augmentation and optimization method based on conditional generative adversarial network and convolutional neural network for transformer fault diagnosis.Measurement,2025,254117872-117872. [2] Zhao T ,Chen T ,Ma D , et al. On line monitoring method for overheating fault of oil immersed transformer based on oil’s chromatographic data.Measurement,2025,253(PB):117603-117603. [3] Shang H , Zhao Z , Zhang R , et al. Transformer partial discharge fault diagnosis based on improved adaptive local iterative filtering‐bidirectional long short‐term memory. IET Electric Power Applications,2024,18(10):1214-1232. [4] Fatma L, Lotfi M , Wiem A , et al. Investigating Machine Learning and Control Theory Approaches for Process Fault Detection: A Comparative Study of KPCA and the Observer-Based Method. Sensors (Basel, Switzerland),2023,23(15): [5] Lan Q ,Zhu Y ,Lin B , et al. Fault Prediction for Rotating Mechanism of Satellite Based on SSA and Improved Informer. Applied Sciences,2024,14(20):9412-9412. [6] Jingbo G , Kunyu Z , Xuejiao D , et al. Detection of gear fault severity based on parameter-optimized deep belief network using sparrow search algorithm.Measurement,2021,185 [7] Zichang L ,Siyu L ,Rongcai W , et al.Research on Fault Feature Extraction Method of Rolling Bearing Based on SSA–VMD–MCKD. Electronics, 2022, 11(20): 3404-3404. [8] Zhao Y ,Jiang A ,Jiang W , et al. Hydraulic pump fault diagnosis by modified slime mold algorithm optimized support vector machine. Measurement, 2025, 254117878-117878. [9] Xu J , Zhu J ,Wang Z .Fault Diagnosis of Switching Power Supplies Using Dynamic Wavelet Packet Transform and Optimized SVM.Sensors,2025,25(10):3236-3236. [10] 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.