Fault Diagnosis of Power Equipment Based on Improved SVM Algorithm

Youle Song; Yuting Duan; Tong Rao

doi:10.4108/ew.7185

Authors

Youle Song Electric Power Research Institute of Yunnan Power Grid, Kunming, 650000, China
Yuting Duan Electric Power Research Institute of Yunnan Power Grid
Tong Rao Electric Power Research Institute of Yunnan Power Grid

DOI:

https://doi.org/10.4108/ew.7185

Keywords:

Support vector machine, Grey wolf optimization algorithm, Modal decomposition, Power equipment, Fault diagnosis

Abstract

Fault diagnosis of power equipment is a crucial task to credit the safe and stable operation of equipment. However, fault diagnosis of power equipment faces challenges such as high dimensionality, complexity, and nonlinearity. Therefore, this study proposes an improved support vector machine model, combined with grey wolf optimization algorithm, aimed at improving the accuracy and efficiency of power equipment fault diagnosis. To validate the model’s performance, this study divided a dataset of 3870 power equipment defects into training and testing sets using an 8:2 ratio, with evaluation metrics including accuracy, recall, and F1 score. The results showed that the fault recognition rate of the support vector machine model based on the improved grey wolf optimization algorithm reached 92.76%, with an accuracy close to 0.95 and a loss rate of 0.13. The model exhibited faster convergence speed, as well as better stability and convergence. At the same time, the optimized model had good feature extraction ability on different types of model faults, and the comprehensive recognition error of the model was basically stable in the interval of (-0.005, 0.005). The experiment validates that the research model improves the optimization algorithm through modal decomposition strategy. Meanwhile, the improvement of support vector machine parameter selection has strengthened the recognition and analysis of fault characteristics, providing an effective solution for power equipment fault diagnosis.

Downloads

Download data is not yet available.

References

[1] Chen B, Liu D. Remote Fault Diagnosis Method of Wind Power Generation Equipment Based on Internet of Things. Journal of Information Processing Systems, 2022, 18(6): 822-829.

[2] Ma F, Wu X, Ni H, Zhou X, Wu H. Research and application of intermittent partial discharge characteristics and easy-warning system for electric equipment. Energy Reports, 2022, 8(1): 217-226.

[3] Kumar V T R P, Arulselvi M, Sastry K B S. Comparative Assessment of Colon Cancer Classification Using Diverse Deep Learning Approaches. Journal of Data Science and Intelligent Systems, 2023, 1(2): 128-135.

[4] Enesi M R, Shehu G S, Abdulkarim A, Jibril Y. Reliability modeling and analysis of high voltage power equipment: a case study of Ajaokuta Steel Company Limited (ASCL). Life Cycle Reliability and Safety Engineering, 2022, 11(4): 377-387.

[5] Meng F, Yang S, Wang J, Xia L, Liu H. Creating knowledge graph of electric power equipment faults based on BERT–BiLSTM–CRF model. Journal of Electrical Engineering & Technology, 2022, 17(4): 2507-2516.

[6] Baek M, Kim S B. Failure detection and primary cause identification of multivariate time series data in semiconductor equipment. IEEE Access, 2023, 11(1): 54363-54372.

[7] Ma F, Wu X, Ni H, Zhou X, Wu H. Research and application of intermittent partial discharge characteristics and easy-warning system for electric equipment. Energy Reports, 2022, 8(1): 217-226.

[8] Kurani A, Doshi P, Vakharia A, Shah M. A comprehensive comparative study of artificial neural network (ANN) and support vector machines (SVM) on stock forecasting. Annals of Data Science, 2023, 10(1): 183-208.

[9] Zhang H, Zou Q, Ju Y, Song C, Chen D. Distance-based support vector machine to predict DNA N6-methyladenine modification. Current Bioinformatics, 2022, 17(5): 473-482.

[10] Avcı C, Budak M, Yağmur N, Balçık F. Comparison between random forest and support vector machine algorithms for LULC classification. International Journal of Engineering and Geosciences, 2023, 8(1): 1-10.

[11] Elen A, Baş S, Közkurt C. An adaptive Gaussian kernel for support vector machine. Arabian Journal for Science and Engineering, 2022, 47(8): 10579-10588.

[12] Dada E, Joseph S, Oyewola D, Fadele A. Application of grey wolf optimization algorithm: recent trends, issues, and possible horizons. Gazi University Journal of Science, 2022, 35(2): 485-504.

[13] Zamfirache I A, Precup R E, Roman R C, Petriu E M. Policy iteration reinforcement learning-based control using a grey wolf optimizer algorithm. Information Sciences, 2022, 585(1): 162-175.

[14] Ahmadi B, Younesi S, Ceylan O, Ozdemir A. An advanced Grey Wolf Optimization Algorithm and its application to planning problem in smart grids. Soft computing: A fusion of foundations, methodologies and applications, 2022, 26(8):3789-2808.

[15] Sharma I, Kumar V, Sharma S. A comprehensive survey on grey wolf optimization. Recent Advances in Computer Science and Communications (Formerly: Recent Patents on Computer Science), 2022, 15(3): 323-333.

[16} Samantaray S, Sahoo A. Prediction of flow discharge in Mahanadi River Basin, India, based on novel hybrid SVM approaches. Environment, Development and Sustainability, 2024, 26(7): 18699-18723.

[17] Zhang Y, Xu P, Liu J, He J, Yang H, Zeng Y, He Y, Yang C. Comparison of LR, 5-CV SVM, GA SVM, and PSO SVM for landslide susceptibility assessment in Tibetan Plateau area, China. Journal of Mountain Science, 2023, 20(4): 979-995.

[18] Zhou J, Yang P, Peng P, Khandelwal M, Qiu Y. Performance evaluation of rockburst prediction based on PSO-SVM, HHO-SVM, and MFO-SVM hybrid models. Mining, Metallurgy & Exploration, 2023, 40(2): 617-635.

[19] Huang Y, Luo J, Ma Z, Tang B, Zhang K, Zhang J. On combined PSO-SVM models in fault prediction of relay protection equipment. Circuits, Systems, and Signal Processing, 2023, 42(2): 875-891.

[20] Alsumaidaee Y A M, Paw J K S, Yaw C T, Tiong S K, Chen C P, Yusaf T, et al. Fault detection for medium voltage switchgear using a deep learning Hybrid 1D-CNN-LSTM model. IEEE Access, 2023, 11(1): 97574-97589.