MCA-KAN: A Novel Classification Method for Power Quality Disturbances

Bin Wang

doi:10.54097/7wdg2h25

Authors

Bin Wang

DOI:

https://doi.org/10.54097/7wdg2h25

Keywords:

BP Neural Network, Prediction, MCA-KAN, Power Quality Disturbance

Abstract

With the widespread integration of distributed power systems and renewable energy, power quality disturbance (PQD) problems are becoming increasingly serious. Most existing PQD classification methods rely on the extraction of single time-domain or frequency-domain features, lacking effective cross-domain information fusion, and their classification accuracy significantly decreases under noise interference. To address this issue, this paper proposes a power quality disturbance classification model (MCA-KAN) based on a multi-channel attention mechanism and a KAN network. This model employs parallel time-domain and frequency-domain feature extraction structures, utilizing 1D-CNN and BiLSTM to capture time- and frequency-domain features respectively, and introducing a cross-attention mechanism to achieve adaptive fusion of time-domain and frequency-domain features. Furthermore, the model uses a KANLinear layer for nonlinear mapping to enhance its classification ability and robustness in high-noise environments. To verify the model's robustness, this paper constructs a noisy dataset under three signal-to-noise ratios (SNR=20dB, 30dB, 50dB) and conducts comparative experiments. The results show that the proposed MCA-KAN achieves an accuracy of 97.82% at an SNR of 20dB, and maintains stable recognition performance at higher SNRs. Compared with existing methods, the proposed network outperforms existing methods in terms of classification accuracy and robustness.

Downloads

Download data is not yet available.

References

[1] Han Yu, Zhou Qian, Li Yong, et al. Analysis of power quality issues and quantified evaluation of additional losses in low-voltage distribution networks for household photovoltaic integration [J]. Journal of Electric Power Science and Technology, 2024,39(03):177-186.

[2] Mahela O P, Shaik A G, Gupta N. A critical review of detection and classification of power quality events[J]. Renewable and Sustainable Energy Reviews, 2015, 41: 495-505.

[3] Zhang Y, Zhang Y, Zhou X. Classification of power quality disturbances using visual attention mechanism and feed-forward neural network[J]. Measurement, 2022, 188: 110390.

[4] Wang Y. A Review of Research on Power Quality Disturbance Detection [J]. Power System Protection and Control, 2021,49(13):174-186.

[5] Wang M, Zhou H, Yang S, et al. Robust compressive features based power quality events classification with Analog–Digital Mixing Network (ADMN)[J]. Neurocomputing, 2016, 171: 685-692.

[6] Sun Dong, Gao Qingwei, Zhu De, et al. Adaptive cyclic power harmonic analysis algorithm based on discrete Fourier transform [J]. Journal of Anhui University (Natural Science Edition), 2013,37(06):57-64.

[7] De Yong D, Bhowmik S, Magnago F. An effective power quality classifier using wavelet transform and support vector machines[J]. Expert Systems with Applications, 2015, 42(15-16): 6075-6081.

[8] Xu Liwu, Li Kaicheng, Luo Yi, et al. Composite power quality disturbance recognition based on incomplete S-transform and gradient boosting tree [J]. Power System Protection and Control, 2019,47(06):24-31.

[9] Samanta I S, Rout P K, Swain K, Samanta I S, Rout P K, Swain K, et al. Power quality events recognition using enhanced empirical mode decomposition and optimized extreme learning machine[J]. Computers and Electrical Engineering, 2022, 100: 107926.

[10] Carní D L, Lamonaca F. Toward an automatic power quality measurement system: An effective classifier of power signal alterations[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-8.

[11] Sahani M, Dash P K. Automatic power quality events recognition using modes decomposition based online P-norm adaptive extreme learning machine[J]. IEEE Transactions on Industrial Informatics, 2019, 16(7): 4355-4364.

[12] Gonzalez-Abreu A D, Saucedo-Dorantes J J, Osornio-Rios R A, et al. Condition monitoring approach based on dimensionality reduction techniques for detecting power quality disturbances in cogeneration systems[C]//2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA). IEEE, 2019: 898-903.

[13] Minh Khoa N, Van Dai L. Detection and classification of power quality disturbances in power system using modified-combination between the stockwell transform and decision tree methods[J]. Energies, 2020, 13(14): 3623.

[14] Choudhary B. Choudhary B. An advanced genetic algorithm with improved support vector machine for multi-class classification of real power quality events[J]. Electric Power Systems Research, 2021, 191: 106879.

[15] Lin L, Wang D, Zhao S, Lin L, Wang D, Zhao S, et al. Power quality disturbance feature selection and pattern recognition based on image enhancement techniques[J]. Ieee Access, 2019, 7: 67889-67904.

[16] Cai K, Cao W, Aarniovuori L, Cai K, Cao W, Aarniovuori L, et al. Classification of power quality disturbances using Wigner-Ville distribution and deep convolutional neural networks[J]. IEEe Access, 2019, 7: 119099-119109.

[17] Shukla J, Panigrahi B K, Ray P K. Power quality disturbances classification based on Gramian angular summation field method and convolutional neural networks[J]. International Transactions on Electrical Energy Systems, 2021, 31(12): e13222.

[18] Yuan D, Liu Y, Lan M, Yuan D, Liu Y, Lan M, et al. A novel recognition method for complex power quality disturbances based on visualization trajectory circle and machine vision[J]. IEEE transactions on instrumentation and measurement, 2022, 71: 1-13.

[19] Zhou L, Gu S, Liu Y, et al. A novel recognition method for complex power quality disturbances based on Markov transition field and improved densely connected network[J]. Frontiers in Energy Research, 2024, 12: 1328994.

[20] Mohan N, Soman K P, Vinayakumar R. Deep power: Deep learning architectures for power quality disturbances classification[C]//2017 international conference on technological advancements in power and energy (TAP Energy). IEEE, 2017: 1-6.

[21] Chiam D H, Lim K H, Law K H. LSTM power quality disturbance classification with wavelets and attention mechanism[J]. Electrical Engineering, 2023, 105(1): 259-266.

[22] Cabral T W, Gomes F V, de Lima E R, Cabral T W, Gomes F V, de Lima E R, et al. Kolmogorov–Arnold Network in the Fault Diagnosis of Oil-Immersed Power Transformers[J]. Sensors, 2024, 24(23): 7585.