本文提出了用於準確檢測電力系統中各種短路故障的資料預處理方法，以實現全面且廣泛地配電系統故障分類。所提方法使用短時距傅立葉轉換(short-time Fourier transform, STFT)將所測量之時域三相電壓和電流信號轉換為時頻域信號以生成時頻能量圖。接著，使用卷積神經網絡(convolutional neural network, CNN)進行特徵提取，並實現故障分類。本研究亦提出一種基於快速動態時間規整(fast dynamic time warping, Fast-DTW)的資料縮減方法，透過比較波形特徵的相似度，將高度相似的數據從資料庫中移除。模擬結果顯示，所提方法能夠有效提高模型的泛化能力，並有效減少訓練時間。本文在兩個環境中實現配電系統建構與模擬，包括暫態分析模擬軟體PSCAD/EMTDC以及實時數位模擬器(real-time digital simulator, RTDS)，而基於STFT的時頻分析則在MATLAB環境中實現。模擬結果顯示，該方法減少了資料庫中40.2%的冗餘數據，同時減少了模型訓練時間。此外，故障分類的整體準確率、精確率、召回率及F1分數分別達到99.37%、99.36%、99.35%及99.35%，證明了所提方法的有效性。

This study proposes a data preprocessing method for accurately detecting various types of short-circuit faults in power systems, which can lead to more effective power repair and maintenance processes. The proposed method involves converting the measured voltage and current signals into time and frequency domains using the short-time Fourier transform (STFT) to produce a time-frequency energy map. A convolutional neural network (CNN) is subsequently trained and tested to classify the short-circuit faults. This study proposes a data reduction method based on the fast dynamic time warping (Fast-DTW) algorithm, which compares waveform features and eliminates highly similar data regarded as redundant data from the dataset. The simulation results show that the proposed method can improve the model training performance and its adaptability to different power system topologies, as tested in two simulation environments: power systems computer-aided design (PSCAD)/electro-magnetic transients, including DC (EMTDC), and the real-time digital simulator (RTDS). The STFT transformation is implemented in MATLAB. The simulation results demonstrate that the proposed method reduces redundant data by 40.2%, while decreasing the model training time. Consequently, the overall accuracy, precision, recall and F1 score of the fault classification reaches 99.37%, 99.36%, 99.35% and 99.35%, confirming the effectiveness of the proposed method for fault classification.

[1] M. Ali, K. Kaur, M. Adnan, and S. Nisar, "Adaptive Fuzzy Controller Based Early Detection and Prevention of Asymmetrical Faults in Power Systems," Control Engineering Practice, vol. 130, Jan. 2023.
[2] M. F. Guo, N. C. Yang, and L. X. You, "Wavelet-Transform Based Early Detection Method for Short-circuit Faults in Power Distribution Networks," International Journal of Electrical Power & Energy Systems, vol. 99, pp. 706-721, Jul. 2018.
[3] M. F. Guo and N. C. Yang, "Features-Clustering-Based Earth Fault Detection using Singular-Value Decomposition and Fuzzy C-means in Resonant Grounding Distribution Systems," International Journal of Electrical Power & Energy Systems, vol. 93, pp. 97-108, Dec. 2017.
[4] A. Ghaderi, H. A. Mohammadpour, H. L. Ginn, and Y. J. Shin, "High-Impedance Fault Detection in the Distribution Network Using the Time-Frequency-Based Algorithm," IEEE Transactions on Power Delivery, vol. 30, no. 3, pp. 1260-1268, Jun. 2015.
[5] Q. M. Xiao, M. F. Guo, and D. Y. Chen, "High-Impedance Fault Detection Method Based on One-Dimensional Variational Prototyping-Encoder for Distribution Networks," IEEE Systems Journal, vol. 16, no. 1, pp. 966-976, Mar. 2022.
[6] Y. H. Xi et al., "Transmission Line Fault Detection and Classification Based on SA-MobileNetV3," Energy Reports, vol. 9, pp. 955-968, Dec. 2023.
[7] Y. L. Wang, X. D. Wang, Y. J. Wu, and Y. N. Guo, "Power System Fault Classification and Prediction Based on a Three-Layer Data Mining Structure," IEEE Access, vol. 8, pp. 200897-200914, 2020.
[8] C. Hong, Z. Y. Zeng, Y. Z. Fu, and M. F. Guo, "Deep-Belief-Networks Based Fault Classification in Power Distribution Networks," IEEJ Transactions on Electrical and Electronic Engineering, vol. 15, no. 10, pp. 1428-1435, Oct. 2020.
[9] P. Rai, N. D. Londhe, and R. Raj, "Fault Classification in Power System Distribution Network Integrated with Distributed Generators using CNN," Electric Power Systems Research, vol. 192, Mar. 2021.
[10] P. Srikanth and C. Koley, "A Novel Three-Dimensional Deep Learning Algorithm for Classification of Power System Faults," Computers & Electrical Engineering, vol. 91, May 2021.
[11] A. Said, S. Hashima, M. M. Fouda, and M. H. Saad, "Deep Learning-Based Fault Classification and Location for Underground Power Cable of Nuclear Facilities," IEEE Access, vol. 10, pp. 70126-70142, 2022.
[12] S. Fuada, H. A. Shiddieqy, and T. Adiono, "A High-Accuracy of Transmission Line Faults (TLFs) Classification Based on Convolutional Neural Network," International Journal of Electronics and Telecommunications, vol. 66, no. 4, pp. 655-664, 2020.
[13] P. Avagaddi and J. B. Edward, "Fault Classification in Transmission Systems using Wavelet Transform," Gazi University Journal of Science, vol. 32, no. 3, pp. 884-893, 2019.
[14] C. Lin, W. Gao, and M. F. Guo, "Discrete Wavelet Transform-Based Triggering Method for Single-Phase Earth Fault in Power Distribution Systems," IEEE Transactions on Power Delivery, vol. 34, no. 5, pp. 2058-2068, Oct. 2019.
[15] T. S. Abdelgayed, W. G. Morsi, and T. S. Sidhu, "A New Harmony Search Approach for Optimal Wavelets Applied to Fault Classification," IEEE Transactions on Smart Grid, vol. 9, no. 2, pp. 521-529, Mar. 2018.
[16] M. F. Guo, X. D. Zeng, D. Y. Chen, and N. C. Yang, "Deep-Learning-Based Earth Fault Detection Using Continuous Wavelet Transform and Convolutional Neural Network in Resonant Grounding Distribution Systems," IEEE Sensors Journal, vol. 18, no. 3, pp. 1291-1300, Feb. 2018.
[17] F. Alvarez-Gonzalez, A. Griffo, and B. Wang, "Permanent Magnet Synchronous Machine Stator Windings Fault Detection by Hilbert-Huang Transform," Journal of Engineering-Joe, no. 17, pp. 3505-3509, Jun. 2019.
[18] M. F. Guo, N. C. Yang, and W. F. Chen, "Deep-Learning-Based Fault Classification Using Hilbert-Huang Transform and Convolutional Neural Network in Power Distribution Systems," IEEE Sensors Journal, vol. 19, no. 16, pp. 6905-6913, Aug. 2019.
[19] O. R. Seryasat, M. A. Shoorehdeli, M. Ghane, J. Haddadnia, and M. Zeinali, "Intelligent Fault Detection of Ball bearing Using FFT, STFT Energy Entropy and RMS," Life Science Journal-Acta Zhengzhou University Overseas Edition, vol. 9, no. 3, pp. 1781-1786, 2012.
[20] R. F. Ribeiro, I. A. D. Areias, M. M. Campos, C. E. Teixeira, L. E. B. da Silva, and G. F. Gomes, "Fault Detection and Diagnosis in Electric Motors Using Convolution Neural Network and Short-Time Fourier Transform," Journal of Vibration Engineering & Technologies, vol. 10, no. 7, pp. 2531-2542, Oct. 2022.
[21] A. Maqsood, D. Oslebo, K. Corzine, L. Parsa, and Y. Ma, "STFT Cluster Analysis for DC Pulsed Load Monitoring and Fault Detection on Naval Shipboard Power Systems," IEEE Transactions on Transportation Electrification, vol. 6, no. 2, pp. 821-831, Jun. 2020.
[22] T. Arias-Vergara, P. Klumpp, J. C. Vasquez-Correa, E. Noth, J. R. Orozco-Arroyave, and M. Schuster, "Multi-Channel Spectrograms for Speech Processing Applications using Deep Learning Methods," Pattern Analysis and Applications, vol. 24, no. 2, pp. 423-431, May 2021.
[23] N. Lopac, F. Hrzic, I. P. Vuksanovic, and J. Lerga, "Detection of Non-Stationary GW Signals in High Noise From Cohen's Class of Time-Frequency Representations Using Deep Learning," IEEE Access, vol. 10, pp. 2408-2428, 2022.
[24] H. Jung and J. Ju, "Training Data Reduction for Deep Learning-Based Image Classifications using Random Sample Consensus," Journal of Electronic Imaging, vol. 31, no. 1, Jan. 2022.
[25] M. T. Zeegers, D. M. Pelt, T. van Leeuwen, R. van Liere, and K. J. Batenburg, "Task-Driven Learned Hyperspectral Data Reduction Using End-to-End Supervised Deep Learning," Journal of Imaging, vol. 6, no. 12, Dec. 2020.
[26] H. H. Li, J. X. Liu, Z. L. Yang, R. W. Liu, K. F. Wu, and Y. Wan, "Adaptively Constrained Dynamic Time Warping for Time Series Classification and Clustering," Information Sciences, vol. 534, pp. 97-116, Sep. 2020.
[27] Y. S. Jeong, M. K. Jeong, and O. A. Omitaomu, "Weighted Dynamic Time Warping for Time Series Classification," Pattern Recognition, vol. 44, no. 9, pp. 2231-2240, Sep. 2011.
[28] S. Salvadora and P. Chan, "Toward Accurate Dynamic Time Warping in Linear Time and Space," Intelligent Data Analysis, vol. 11, no. 5, pp. 561-580, 2007.
[29] X. Zhang, Z. L. Li, N. Nan, and X. Z. Wang, "Depth-Resolved Dispersion Compensation Method for Optical Coherence Tomography Imaging Based on Rectangular Window Function Optimization," Journal of Modern Optics, vol. 69, no. 15, pp. 827-837, Sep. 2022.
[30] W. Astuti, W. Sediono, A. M. Aibinu, R. Akmeliawati, M. J. E. Salami, and Ieee, "Adaptive Short Time Fourier Transform (STFT) Analysis of Seismic Electric Signal (SES): A Comparison of Hamming and Rectangular Window," in IEEE Symposium on Industrial Electronics and Applications (ISIEA), Bandung, INDONESIA, Sep. 23-26 2012, 2012.