Safety risk point identification and localization in power equipment based on electromagnetic signals and a multiscale attention convolutional neural network
DOI:
https://doi.org/10.4108/ew.14304Keywords:
power equipment, electromagnetic signals, risk point identification, multiscale convolution, attention fusionAbstract
INTRODUCTION: Safety risk points in power equipment often produce weak and non-stationary electromagnetic responses. These responses are difficult to identify when partial discharge, contact anomalies, insulation deterioration, and shielding defects occur under complex operating conditions.
OBJECTIVES: To improve risk recognition and spatial localization, a multichannel electromagnetic signal identification method is proposed.
METHODS: Sliding windows are used to construct signal samples. Outlier correction, normalization, and wavelet threshold denoising are then performed to suppress background interference while preserving transient pulse structures. Time-domain statistics, frequency-domain energy characteristics, and short-time Fourier transform (STFT) spectra are extracted to describe waveform fluctuation, band energy migration, and time-frequency coupling. A multiscale convolutional neural network (CNN) with an attention mechanism is designed to enhance key frequency bands and sensitive measurement channels. Spatial correlation weights are further introduced to estimate the location of risk points.
RESULTS: Experimental results show that the proposed method achieves a recognition accuracy of 95.28%, an F1-score of 94.58%, and an area under the receiver operating characteristic curve (AUC) of 0.981. The mean localization error is 8.46 cm.
CONCLUSION: Compared with conventional methods, the proposed method improves the discrimination of weak electromagnetic disturbances and provides a practical solution for safety risk identification in power equipment.
Downloads
References
[1] Hussain G A, Hassan W, Mahmood F, et al. Review on partial discharge diagnostic techniques for high voltage equipment in power systems[J]. IEEE Access, 2023, 11: 51382-51394.
[2] Kumar H, Shafiq M, Kauhaniemi K, et al. A review on the classification of partial discharges in medium-voltage cables: detection, feature extraction, artificial intelligence-based classification, and optimization techniques [J]. Energies, 2024, 17(5): 1142.
[3] Rauscher A, Kaiser J, Devaraju M, et al. Deep learning and data augmentation for partial discharge detection in electrical machines[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108074.
[4] Carvalho I F, da Costa E G, Nobrega L A M M, et al. Identification of partial discharge sources by feature extraction from a signal conditioning system [J]. Sensors, 2024, 24(7): 2226.
[5] Khodaveisi F, Karami H, Karimpour M Z, et al. Partial discharge localization in power transformer tanks using machine learning methods [J]. Scientific Reports, 2024, 14(1): 11785.
[6] Almehdhar A, Prochazka R. Classification of multiple partial discharge sources using time-frequency analysis and deep learning [J]. Applied Sciences, 2025, 15(10): 5455.
[7] Li A, Wei G, Li S, et al. Pattern recognition of partial discharge in high-voltage cables using TFMT model [J]. IEEE Transactions on Power Delivery, 2024, 39(6): 3326-3337.
[8] Das R, Das A K, Chatterjee S, et al. A novel deep-learning framework to identify and locate single and multiple partial discharge events [J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2023, 30(6): 2633-2641.
[9] Govindarajan S, Morales A, Ardila-Rey J A, et al. A review on partial discharge diagnosis in cables: Theory, techniques, and trends [J]. Measurement, 2023, 216: 112882.
[10] Tag A, Refaat S S, Kameli S M, et al. Machine learning applications for online partial discharge detection, classification, and localization in power transformers: A review[C]//2024 4th International Conference on Smart Grid and Renewable Energy (SGRE). IEEE, 2024: 1-6.
[11] Thobejane L T, Thango B A. Partial discharge source classification in power transformers: A systematic literature review [J]. Applied Sciences, 2024, 14(14): 6097.
[12] Sahoo R, Karmakar S. Comparative analysis of machine learning and deep learning techniques on classification of artificially created partial discharge signal [J]. Measurement, 2024, 235: 114947.
[13] Hassan W, Hussain G A, Wahid A, et al. Optimum feature selection for classification of PD signals produced by multiple insulation defects in electric motor s[J]. Scientific Reports, 2024, 14(1): 23446.
[14] Ortego J, Garnacho F, Álvarez F, et al. Locating Insulation Defects in HV Substations Using HFCT Sensors and AI Diagnostic Tools[J]. Sensors, 2024, 24(16): 5312.
[15] Dalila R A M, Turkben A K. Artificial intelligence based partial discharge detection using CNN and KNN to increase the quality of electrical insulation [J]. Discover Computing, 2025, 28(1): 101.
[16] Kaziz S, Said M H, Imburgia A, et al. Radiometric partial discharge detection: A review [J]. Energies, 2023, 16(4): 1978.
[17] Jung H, Kim Y T, Lee S K, et al. Study on deep-learning model for phase resolved partial discharge pattern classification based on convolutional neural network algorithm [J]. Journal of Electrical Engineering & Technology, 2025, 20(1): 873-878.
[18] Aldosari O, Aldowsari M A, Batiyah S M, et al. Image-based partial discharge identification in high voltage cables using hybrid deep network [J]. Ieee Access, 2023, 11: 50325-50333.
[19] Liu K, Jiao S, Nie G, et al. On image transformation for partial discharge source identification in vehicle cable terminals of high‐speed trains [J]. High Voltage, 2024, 9(5): 1090-1100.
[20] Hu D, Chen Z, Yang W, et al. A GIS Partial Discharge Pattern Recognition Method Based on Improved CBAM‐ResNet [J]. Journal of Electrical and Computer Engineering, 2023, 2023(1): 9948438.
[21] Zhang C, Chen M, Zhang Y, et al. Partial discharge pattern recognition algorithm of overhead covered conductors based on feature optimization and bidirectional LSTM‐GRU [J]. IET Generation, Transmission & Distribution, 2024, 18(4): 680-693.
[22] Beura C P, Wolters J, Tenbohlen S. Application of pathfinding algorithms in partial discharge localization in power transformers [J]. Sensors, 2024, 24(2): 685.
[23] Monzón-Verona J M, González-Domínguez P, García-Alonso S. Characterization of partial discharges in dielectric oils using high-resolution CMOS image sensor and convolutional neural networks [J]. Sensors, 2024, 24(4): 1317.
[24] Klein L, Seidl D, Fulneček J, et al. Antenna contactless partial discharges detection in covered conductors using ensemble stacking neural networks[J]. Expert Systems with Applications, 2023, 213: 118910.
[25] Saad M H, Hashima S, Omar A I, et al. Deep learning approach for cable partial discharge pattern identification [J]. Electrical Engineering, 2025, 107(2): 1525-1540.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Siwu Yu, Fan Song, Xing Liu, Yang Mei, Jiangang Liu, Yuanyuan Zhao, Siqi Guo, Yumin He
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
