Abstract
Aiming at the problem of low accuracy of fault identification due to poor feature extraction ability of existing fault identification methods for infrared images of electrical equipment, a fault identification method for infrared images of electrical equipment based on improved BEMD frequency domain decomposition was proposed. Firstly, to solve the shortcoming of slow operation speed of BEMD, we improve BEMD to generate mean envelope surface directly through sequential statistical filter and Gaussian filter, and decompose infrared image of electrical equipment in fast frequency domain. Secondly, based on the improved BEMD method, Res-LSTM network is constructed to identify the faults of electrical equipment. ResNet is used to extract the features from the infrared images of electrical equipment, and LSTM network is used to diagnose the faults of extracted features. Finally, the proposed method is verified by experiments, and the experimental results show that the improved BEMD can significantly improve the computing speed compared with the traditional BEMD. Compared with the single Res-LSTM network, the fault identification accuracy of the Res-LSTM network based on the improved BEMD frequency domain decomposition is improved.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Xia, C., Ren, M., Wang, B., et al.: Infrared thermography‐based diagnostics on power equipment: State-of‐the-art. High Voltage. (2020)
Yujie, L., Hongtao, L., Siqi, S., et al.: Temperature detection of internal conductor in GIS based on infrared thermal imaging. Electr. Power Eng. Technol. 38(02), 142–146 (2019). (in Chinese)
Žarković, M., Stojković, Z.: Analysis of artificial intelligence expert systems for power transformer condition monitoring and diagnostics. Electr. Power Syst. Res. 149, 125–136 (2017)
Bouazza, H., et al.: Application of artificial intelligence to wind power generation: modelling, control and fault detection. Int. J. Intell. Syst. Technol. Appl. 19(3), 280–305 (2020)
Wong, S.Y., et al.: Power transmission line fault detection and diagnosis based on artificial intelligence approach and its development in UAV: A review. Arabian J. Sci. Eng. 46(10), 1–27 (2021)
Feng, Z., Zhou, D., Jiang, Y., et al.: Fault region extraction using improved MSER algorithm with application to the electrical system. Power Syst. Prot. Control. 47(05), 123–128 (2019). (in Chinese)
Ying, L., Zhihong, G., Yufeng, C.: Convolutional-recursive network based current transformer infrared fault image diagnosis. Power Syst. Prot. Control. 43(16), 87–94 (2015). (in Chinese)
Zhao, Z.B., Wang, Q., Yu, P., et al.: Registration research of infrared/visible image of power equipment based on BEMD. Power Syst. Prot. Control 39(23), 25–29 (2011). (in Chinese)
Nunes, J.C., Bouaoune, Y., Delechelle, E., et al.: Image analysis by bidimensional empirical mode decomposition. Image Vis. Comput. 21(12), 1019–1026 (2003)
Huangn, E., Shen, Z., Long, S.R., et al.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. Math. Phys. Eng. Sci. 1998(454), 903–995 (1971)
Chuanjin, H., Haijun, S., Na, Q.: BEMD full vector envelope spectrum and its application in TRT fault diagnosis. Electr. Power Autom. Equipment 38(01), 184–192 (2018). (in Chinese)
Deyou, Y., Ziang, G., Yinxuan, L.: Interval prediction of wind power based on bivariate empirical mode decomposition and least squares support vector machine. Electr. Power Constr. 40(05), 118–127 (2019). (in Chinese)
Yupeng, C., Lin, L., Qiao, W., et al.: Fault diagnosis of high-voltage vacuum circuit breaker with a convolutional deep network. Power Sys. Prot. Control. 49(03), 39–47 (2021). (in Chinese)
Bhuiyan, S.M.A., Adhami, R.R., Khan, J.F.: Fast and adaptive bidimensional empirical mode decomposition using order-statistics filter based envelope estimation. EURASIP J. Adv. Signal Process. 2008(1), 1–18 (2008)
Xiaodong, G., Danhong, T., Xiaohua, H.: Deep learning-based defect detection and recognition of a power grid inspection image. Power Syst. Prot. Control 49(05), 91–97 (2021). (in Chinese)
Ying, Z., Yili, X., Wenjiang, P.: Fusion of infrared and color images based on improved BEMD. Comput. Sci. 47(03), 124–129 (2020). (in Chinese)
Huiling, Z., Zhewen, N., Kecan, H., et al.: Target recognition and localization in infrared image of electrical equipment based on single-stage target detection algorithm. Electr. power autom. equipment 8, 1–8 (2021). (in Chinese)
He, K., Zhang, X., Ren, S., Sun, J.: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, Y., Liu, Y., Li, G., Xie, J., Yang, T. (2022). Res-LSTM Infrared Image Fault Identification Method Based on Improved BEMD Frequency Domain Decomposition. In: He, J., Li, Y., Yang, Q., Liang, X. (eds) The proceedings of the 16th Annual Conference of China Electrotechnical Society. Lecture Notes in Electrical Engineering, vol 891. Springer, Singapore. https://doi.org/10.1007/978-981-19-1532-1_92
Download citation
DOI: https://doi.org/10.1007/978-981-19-1532-1_92
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1531-4
Online ISBN: 978-981-19-1532-1
eBook Packages: EngineeringEngineering (R0)