CHENG Jiangzhou, HU Xingyu, LI Xin, et al. Composite Power Quality Disturbance Identification Method Based on A Time-Frequency Feature Fusion Classification Network[J]. 2025, 53(7): 115-123.
CHENG Jiangzhou, HU Xingyu, LI Xin, et al. Composite Power Quality Disturbance Identification Method Based on A Time-Frequency Feature Fusion Classification Network[J]. 2025, 53(7): 115-123. DOI: 10.20204/j.sp.2025.07015.
Composite Power Quality Disturbance Identification Method Based on A Time-Frequency Feature Fusion Classification Network
To address the difficulties in classifying composite power quality disturbances and the issue of low identification accuracy under the "dual-high" characteristics trend (high penetration of renewable energy and power electronics) in new power systems, this paper proposes a composite disturbance identification method based on a time-frequency feature fusion classification network. First, a combined method of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and wavelet thresholding is used to denoise the noisy signals. Second, fast Fourier transform (FFT) is applied to the denoised signals to obtain their frequency-domain components. A TCN-Transformer deep network is then employed to extract the time-domain and frequency-domain deep features of the signals in parallel. Finally, a cross-attention mechanism is introduced to perform the weighted fusion of the time-domain and frequency-domain features, completing the classification and identification. Simulation results demonstrate that the proposed method achieves a maximum identification accuracy of 99.79% for 24 types of simulated signals under 30 dB noise environments, exhibiting excellent identification accuracy, stability, and generalization capabilities.
关键词
Keywords
references
CAICEDO J E,AGUDELO-MARTÍNEZ D,RIVAS-TRUJILLO E,et al.A systematic review of real-time detection and classification of power quality disturbances[J].Protection and Control of Modern Power Systems,2023,8(1):1-37.
SINGH N,ANSARI M A,TRIPATHY M,et al.Feature extraction and classification techniques for power quality disturbances in distributed generation:a review[J].IETE Journal of Research,2023,69(6):3836-3851.
MOLINA M A J ,ARCHUNDIA R E ,GNECCHI G A J ,et al.Optimal selection of sampling rates and mother wavelet for an algorithm to classify power quality disturbances[J].Computers,2025,14(4):138-138.
TOPALOGLU I.Deep learning based a new approach for power quality disturbances classification in power transmission system[J].Journal of Electrical Engineering & Technology,2023,18(1):77-88.
ERISTI B,ERISTI H.A new deep learning method for the classification of power quality disturbances in hybrid power system[J].Electrical Engineering,2022,104(6):3753-3768.
MA J,TANG Q,HE M J,et al.Complex PQD classification using time-frequency analysis and multiscale parallel attention residual network[J].IEEE Transactions on Industrial Electronics,2023,71(8):9658-9667.