Power transformer fault warning combining support vector machine and improved grey wolf optimization algorithm

• Autorzy: Zhao Shuzong , Pattanadech Norasage

Identyfikatory

DOI

10.24425/aee.2025.153019

• Języki publikacji: EN

Abstrakty

EN

To optimize the parameter setting of the support vector machine and improve the classification performance and computational efficiency of power transformer fault diagnosis, this study proposes an improved grey wolf optimization algorithm. By optimizing the global search and local optimization capabilities of the grey wolf algorithm and combining them with stacked denoising autoencoders, a new power transformer fault warning model is constructed. Firstly, the grey wolf optimization algorithm is optimized through four strategies: elite reverse learning, nonlinear control parameters, Lévy flight, and particle swarm optimization, which improve its global search and local optimization capabilities. Secondly, the stacked denoising autoencoder is utilized to extract high-level features of fault data, and the improved GWO algorithm and SVM are combined to complete fault classification. The results indicated that the proposed diagnostic model achieved a diagnostic accuracy of 0.979, a recall rate of 0.986, and an F1 value of 0.983 in benchmark performance testing. In practical applications, the average fault diagnosis accuracy of this model could reach up to 99.21%, and the average diagnosis time was only 0.08 s. The developed power transformer fault warning model can provide an efficient and reliable technical solution for fault diagnosis in the power system.

Słowa kluczowe

EN

fault diagnosis; HGWO; hybrid grey wolf optimizer; SDAE; stacked denoising autoencoder; SVM; support vector machine; transformer

• Wydawca: Polish Academy of Sciences, Committee on Electrical Engineering
• Czasopismo: Archives of Electrical Engineering
• Rocznik: 2025
• Tom: Vol. 74, nr 1
• Strony: 191--208
• Opis fizyczny: Bibliogr. 23 poz., rys., tab., wykr., wz.

Twórcy

autor

Zhao Shuzong

• Faculty of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand

• https://orcid.org/0009-0008-5039-2950

autor

Pattanadech Norasage

• Faculty of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand

• https://orcid.org/0000-0002-3897-1895

Bibliografia

• [1] Deng Y., Ruan J., Dong X., Huang D., Zhang C., Inversion detection method of oil-immersed transformer abnormal heating state, IET Electric Power Applications, vol. 17, no. 1, pp. 134–148 (2023), DOI: 10.1049/elp2.12249.
• [2] Hebbi C., Mamatha H., Comprehensive dataset building and recognition of isolated handwritten kannada characters using machine learning models, Artificial Intelligence and Applications, vol. 1, no. 3, pp. 179–190 (2023), DOI: 10.47852/bonviewAIA3202624.
• [3] Wang C., Wu Z., Huang T., Wu X., Huang H., Research on automatic detection of gradual fault of high voltage electric energy metering transformer based on fuzzy rough set and whale optimization algorithm, Journal of Vibroengineering, vol. 26, no. 3, pp. 551–566 (2024), DOI: 10.21595/jve.2023.23596.
• [4] Yan P., Chen F., Kan X., Zhang H., Wang J., Li G., Research on transformer fault diagnosis based on an IWHO optimized MS1DCNN algorithm and LIF spectrum, Analytical Methods, vol. 15, no. 29, pp. 3562–3576 (2023), DOI: 10.1039/d3ay00713h.
• [5] Yan X., Lin Z., Lin Z., Vucetic B., A novel exploitative and explorative GWO-SVM algorithm for smart emotion recognition, IEEE Internet of Things Journal, vol. 10, no. 11, pp. 9999–10011 (2023), DOI: 10.1109/JIOT.2023.3235356.
• [6] Tang J., Zhao Q., Motor rolling bearing fault diagnosis based on MVMD energy entropy and GWO-SVM, Journal of Vibroengineering, vol. 25, no. 6, pp. 1096–1107 (2023), DOI: 10.21595/jve.2023.23046.
• [7] Liu L., Liu Z., Qian X., Rolling bearing fault diagnosis based on generalized multiscale mean permutation entropy and GWO-LSSVM, IET Science, Measurement & Technology, vol. 17, no. 6, pp. 243–256 (2023), DOI: 10.1049/smt2.12149.
• [8] Hui S., Longxiang Y., Shuangquan G.U.O., GWO-ResNet power transformer fault diagnosis method based on data augmentation and feature attention mechanism, Modern Electric Power, vol. 41, no. 2, pp. 392–400 (2024), DOI: 10.19725/j.cnki.1007-2322.2022.0163.
• [9] Wang H., Yao H., Guo Q., Yu X., Zhang X., Cong L., A transformer fault diagnosis method based on multiscale 1DCNN, Journal of Electric Power Science and Technology, vol. 38, no. 4, pp. 104–112 (2023), DOI: 10.19781/j.issn.1673-9140.2023.04.011.
• [10] Haoran X., Ziyi W., Condition evaluation and fault diagnosis of power transformer based on gan-cnn, Journal of Electrotechnology, Electrical Engineering and Management, vol. 6, no. 3, pp. 8–16 (2023), DOI: 10.23977/jeeem.2023.060302.
• [11] Lu W., Shi C., Fu H., Xu Y., Research on transformer fault diagnosis based on ISOMAP and IChOALSSVM, IET Electric Power Applications, vol. 17, no. 6, pp. 773–787 (2023), DOI: 10.1049/elp2.12302.
• [12] Men Z., Hu C., Li Y.H., Bai X., A hybrid intelligent gearbox fault diagnosis method based on EWCEEMD and whale optimization algorithm-optimized SVM, International Journal of Structural Integrity, vol. 14, no. 2, pp. 322–336 (2023), DOI: 10.1108/IJSI-12-2022-0145.
• [13] Tian H., Wu H., Fault Distance measurement method based on wavelet energy spectrum and BWO algorithm optimized CNN-GRU hybrid neural network, Academic Journal of Science and Technology, vol. 11, no. 1, pp. 247−256 (2024), DOI: 10.54097/s30txd46.
• [14] Seyyedabbasi A., Kiani F., I-GWO and Ex-GWO: improved algorithms of the Grey Wolf Optimizer to solve global optimization problems, Engineering with Computers, vol. 37, no. 1, pp. 509–532 (2021), DOI: 10.1007/s00366-019-00837-7.
• [15] Kalita K., Pal S., Haldar S., Chakraborty S., A hybrid TOPSIS-PR-GWO approach for multi-objective process parameter optimization, Process Integration and Optimization for Sustainability, vol. 6, no. 4, pp. 1011–1126 (2022), DOI: 10.1007/s41660-022-00256-0.
• [16] Ma R., Karimzadeh M., Ghabussi A., Zandi Y., Baharom S., Selmi A., Maureira-Carsalade N., Assessment of composite beam performance using GWO–ELM metaheuristic algorithm, Engineering with Computers, vol. 38, no. 3, pp. 2083–2099 (2022), DOI: 10.1007/s00366-021-01363-1.
• [17] Deng Z., Zhao C., Leng J., Zhai G., Wang X., Evaluation method of transformer insulation aging state based on IWOABP algorithm, Journal of Electric Power Science and Technology, vol. 38, no. 5, pp. 253–261 (2024), DOI: 10.19781/j.issn.1673-9140.2023.05.026.
• [18] Li H., Dou L., Li S., Kang Y., Yang X., Dong H., Abnormal state detection of OLTC based on improved fuzzy C-means clustering, Chinese Journal of Electrical Engineering, vol. 9, no. 1, pp. 129–141 (2023), DOI: 10.23919/CJEE.2023.000002.
• [19] Jin Z., He D., Lao Z., Wei Z., Yin X., Yang W., Early intelligent fault diagnosis of rotating machinery based on IWOA-VMD and DMKELM, Nonlinear Dynamics, vol. 111, no. 6, pp. 5287−5306 (2023), DOI: 10.1007/s11071-022-08109-8.
• [20] Xue R., Cai Y., Optimization of parallel SVM algorithm for big data, Journal of Computational Methods in Sciences and Engineering, vol. 24, no. 2, pp. 1253–1266 (2024), DOI: 10.3233/JCM-247335.
• [21] Liu S., Liu Y., Shan L., Wang Q., Sun Y., He L., Hybrid Conditional Kernel SVM for Wire Rope Defect Recognition, IEEE Transactions on Industrial Informatics, vol. 20, no. 4, pp. 6234–6244 (2024), DOI: 10.1109/TII.2023.3344135.
• [22] Saufi S.R., Isham M.F., Ahmad Z.A., Hasan M.D.A., Machinery fault diagnosis based on a modified hybrid deep sparse autoencoder using a raw vibration time-series signal, Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 4, pp. 3827–3838 (2023), DOI: 10.1007/s12652-022-04436-1.
• [23] Jang J.G., Noh C.M., Kim S.S., Shin S.C., Lee S.S., Lee J.C., Vibration data feature extraction and deep learning-based preprocessing method for highly accurate motor fault diagnosis, Journal of Computational Design and Engineering, vol. 10, no. 1. pp. 204–220 (2023), DOI: 10.1093/jcde/qwac128.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).