Optimization of KELM for Transformer Fault Diagnosis Based on Dung Beetle Optimizer Algorithm

DOI: https://doi.org/10.62517/jbdc.202401414

Author(s)

Xiaopeng Zhang*, Yuan Chai

Affiliation(s)

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

Abstract

Aiming at the problem of inaccurate classification accuracy of existing fault classification models, a Dung Beetle Optimizer (DBO) method is proposed to optimize the Kernel Extreme Learning Machine (KELM) for transformer pattern recognition. Firstly, to address the issue of the KELM method being greatly affected by parameter values during fault classification. The kernel function and regularization coefficient of KELM are determined by using DBO to establish a DBO-KELM diagnosis model, and the fault diagnosis is carried out by using the optimized DBO-KELM diagnosis model, and compared with ABC-KELM and GWO-KELM. The final experimental results show that the diagnosis effect of DBO-KELM is better and the accuracy is higher.

Keywords

DBO; KELM; Sparrow Search Algorithm; Transformer; Fault Diagnosis

References

[1] 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. [2] 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. [3] Liu G, Gao L, Yu L, et al. Research on Transformer Fault Diagnosis Based on Voiceprint Signal. IOP Publishing Ltd, 2024.DOI:10.1088/1742-6596/2774/1/012052. [4] Zou D, Li Z, Quan H, et al. Transformer fault classification for diagnosis based on DGA and deep belief network. Energy Reports, 2023, 9:250-256. DOI: 10.1016/j.egyr.2023.09.183. [5] Feng W, Zhang G, Ouyang Y, et al. Fault Diagnosis of Oil -Immersed Transformer based on TSNE and IBASA-SVM. Recent Patents on Mechanical Engineering, 2022. DOI: 10.2174/2212797615666220622093515. [6] Sun YJ, Zhang, et al. Improved BP Neural Network for Transformer Fault Diagnosis. Journal of China University of Mining & Technology, 2007. DOI: CNKI:SUN:ZHKD.0.2007-01-029. [7] Wang L L, Pei F, Zhu Y L. Transformer Fault Diagnosis Based on Online Sequential Extreme Learning Machine. Applied Mechanics & Materials, 2015, 721: 360-365. DOI: 10.4028/www.scientific.net/AMM.721.360. [8] Wang J, Zhao Z, Zhu J, et al. Improved Support Vector Machine for Voiceprint Diagnosis of Typical Faults in Power Transformers. Machines, 2023, 11(5). DOI: 10.3390/machines11050539. [9] Cheng J, Feng Z, Xiong Y. Transformer Fault Diagnosis Based on an Improved Sine Cosine Algorithm and BP Neural Network. Recent advances in electrical & electronic engineering, 2022. [10] Sun J, Chen H, Sun Z, et al. An electronic nose based on adaptive fusion of transformer-ELM with active temperature modulation algorithm for accurate odor detection in refrigerators. Computers and Electronics in Agriculture, 2023, 214. DOI: 10.1016/j.compag.2023.108343. [11] Wang C, Cai C, Du Y, et al. Fault Diagnosis of Transformer Winding Looseness Based on Vibration Signal and GOA-KELM Model. Journal of Physics: Conference Series, 2022, 2290(1). DOI: 10.1088/1742-6596/2290/1/012089. [12] Han J, Zhu Y, Zhang R, et al. A transformer winding mechanical fault diagnosis method based on ST-SVD and DBO-SVM models. IOP Publishing Ltd, 2024. DOI: 10.1088/1742-6596/2849/1/012052. [13] A S L, A W G, A C H, et al. A newly-designed fault diagnostic method for transformers via improved empirical wavelet transform and kernel extreme learning machine. Advanced Engineering Informatics, 49[2024-12-19]. DOI: 10.1016/j.aei.2021.101320. [14] Fei P, Xue-Zhen C, Yong-Li Z, et al. Transformer fault diagnosis based on particle swarm optimization and kernel-based extreme learning machine. Computer Engineering and Design [2024-12-19]. [15] Xin W, Wenbin C, Min C, et al. Transformer fault diagnosis based on PCA-KELM and AT. China Measurement & Test, 2019.