A Single-phase Grounding Fault Location Method for Active Distribution Networks based on CPCA-CNN

Tengfei Cha

doi:10.6919/ICJE.202602_12(2).0013

Authors

Tengfei Cha

DOI:

https://doi.org/10.6919/ICJE.202602_12(2).0013

Keywords:

Active Distribution Network; Fault Location; Transient Extraction Transform; Attention Mechanism.

Abstract

Aiming at the problems of weak fault features and localization difficulties in active distribution networks, this paper proposes a fault location method that integrates Channel Prior Convolutional Attention (CPCA) and Convolutional Neural Networks (CNN). A Butterworth band-pass filter is utilized to preprocess zero-sequence currents, filtering out power frequency components and high-frequency noise. The one-dimensional transient signals are then transformed into high-dimensional time-frequency images through Transient Extraction Transform (TET). A CNN-based model is constructed to perform deep learning and feature extraction from these images. Generalization tests verify the effectiveness of the proposed method, achieving an overall accuracy of 99.98%.

Downloads

Download data is not yet available.

References

[1] Mirshekali H, Dashti R, Keshavarz A, et al. A novel fault location methodology for smart distribution networks[J]. IEEE Transactions on Smart Grid, 2021, 12(2): 1277-1288.

[2] Yao Z, Liu Y, Chen J, et al. Active high-impedance fault detection method for resonant grounding distribution networks[J]. IEEE Access, 2024, 12: 10932-10945.

[3] Dashti R, Daisy M, Shaker H R, et al. Impedance-based fault location method for four-wire power distribution networks[J]. Ieee Access, 2017, 6: 1342-1349.

[4] Jiang K, Wang H, Shahidehpour M, et al. Block-sparse Bayesian learning method for fault location in active distribution networks with limited synchronized measurements[J]. IEEE Transactions on Power Systems, 2021, 36(4): 3189-3203.

[5] Lin J, Guo M, Zheng Z. Active location method for single-line-to-ground fault of flexible grounding distribution networks[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-12.

[6] Zhang Z, Shi H, Li G, et al. A Method for Identifying The Medium-Voltage Phase-to-Phase Short-Circuit Fault Section in Active Distribution Networks Based on the Equivalent Impedance Ratio of Low-Voltage Monitoring Nodes[J]. IEEE Transactions on Smart Grid, 2025, 16(6): 4534-4548.

[7] Catucuamba J, Téllez A A. Design of a Generic Fault Diagnosis Model for Electrical Distribution Networks Using a Support Vector Machine (SVM) Algorithm[J]. IEEE Access, 2025, 13: 160175-160192.

[8] Jiang K, Wang H, Shahidehpour M, et al. Block-sparse Bayesian learning method for fault location in active distribution networks with limited synchronized measurements[J]. IEEE Transactions on Power Systems, 2021, 36(4): 3189-3203.

[9] Guo M F, Gao J H, Shao X, et al. Location of single-line-to-ground fault using 1-D convolutional neural network and waveform concatenation in resonant grounding distribution systems[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 70: 1-9.

[10] Xu Y, Zhao C, Xie S, et al. Novel fault location for high permeability active distribution networks based on improved VMD and S-transform[J]. IEEE Access, 2021, 9: 17662-17671.

[11] Ma Y, Yu G, Lin T, et al. Synchro-transient-extracting transform for the analysis of signals with both harmonic and impulsive components[J]. IEEE Transactions on Industrial Electronics, 2024, 71(10): 13020-13030.

[12] Huang H, Chen Z, Zou Y, et al. Channel prior convolutional attention for medical image segmentation[J]. Computers in Biology and Medicine, 2024, 178: 108784.