Article Details

Abstract

Aiming at the problems of difficult feature extraction and low recognition efficiency in the recognition process of complex Power Quality Disturbances (PQDs) signals, this paper proposes a high efficiency visualization method and a PQDs recognition method of the lightweight network model. Firstly, the Recurrence Plot (RP) method is utilized to visualize one-dimensional PQDs signals to capture the nonlinear dynamic features in these signals. Secondly, according to IEEE Std 1159—2019 standard, 30 types of PQDs signals are simulated and generated, and the image dataset is established by the RP method. Thirdly, the MobileViT lightweight network is used to perform feature extraction and classification recognition tasks on the custom image dataset. Finally, through comparative experiments and robustness tests with the traditional lightweight networks of MobileNetV2 and MobileNetV3, it is verified that the method adopted in this paper has higher recognition accuracy and faster reasoning speed.

Keywords

PQDs; RP; visualization; MobileViT; lightweight network

References

1. [1] Zhang Xi, Zheng Jianyong, Mei Fei, etc Image analysis based edge cloud collaborative identification framework for power quality disturbances [J/OL]. Chinese Journal of Electrical Engineering, 2025:1-15 [205-06-23] https://link.cnki.net/urlid/11.2107.tm. 20240612.1514.018.
2. [2] Hu Xuefeng, Zhang Liang Composite power quality disturbance identification based on transfer learning and AlexNet [J]. Automation Instrumentation, 2023, 44 (7): 55-60
3. [3] Zhang Yi, Ou Jieyu, Jin Tao, etc A method for identifying power quality disturbances based on feature image combination and improved ResNet-18 [J]. Chinese Journal of Electrical Engineering, 2024, 44 (7): 2531-2545
4. [4] Wang Haidong, Cheng Shan, Xu Qiping, etc A method for identifying noisy power quality disturbances based on deep learning fusion network [J]. Power System Protection and Control, 2024, 52 (10): 11-20
5. [5] Zhu Yong, Tao Yongwei, Li Zequn Identification of power quality disturbances based on S-transform and feature optimization [J]. Electrical Technology, 2023 (21): 97-100
6. [6] Li Qi, Xu Suan, Shi Ge, etc Composite power quality disturbance identification based on S-transform and IWOA-SVM [J]. Smart Power, 2023, 51 (5): 30-35+50
7. [7] Li Jiajun, Wu Jianjun, Chen Wu, etc Classification method of power quality disturbances based on DWT-PCA-LIBSVM [J]. Electrical Engineering, 2023 (3): 20-24
8. [8] Qian Shaofeng, Yao Haiyan, Guo Qiang, etc Research on Power Quality Disturbance Identification Method Based on ITD Decomposition and Twin Support Vector Machine [J]. Electrical Technology, 2023 (13): 21-26+31
9. [9] Yang Xiaomei, Guo Linming, Xiao Xianyong, etc Composite disturbance classification of power quality based on adjustable quality factor wavelet transform and random forest feature selection algorithm [J]. Grid Technology, 2020, 44 (8): 3014-3020
10. [10] Chen Wei, Zhang Yun, Pei Xiping, etc Classification method for power quality disturbances based on case-based reasoning and SVM-KNN [J]. Journal of Lanzhou University of Technology, 2017, 43 (4): 87-92
11. [11] Hecai County, Li Kaicheng, Dong Yufei, etc Composite disturbance identification of power quality based on knowledge distillation and RP MobileNetV3 [J]. Power System Protection and Control, 2023, 51 (14): 75-84
12. [12] Fu Kuan, Wang Hongxin, Liu Jie, etc Identification of composite power quality disturbances based on Markov transition field and EfficientNet [J]. Power Grid and Clean Energy, 2024, 40 (4): 74-83
13. [13] Li Beiao, Li Kaicheng, Xiao Xiangui, etc Composite power quality disturbance identification based on multi-scale convolution fusion time series Transformer [J/OL]. Grid Technology, 2025:1-12 [205-06-20] https://link.cnki.net/doi/10.13335/j.1000-3673.pst.2023.1764.
14. [14] Wang Jidong, Wang Zeping, Zhang Di Classification of Power Quality Disturbances Based on Recursive Graph and Pre trained Transfer Learning [J/OL]. Southern Power Grid Technology, 2025:1-10
15. [2025-01-03].https://link.cnki.net/urlid/44.1643.tk.20240517. 1116.002.

About the authors

Liu Daoqing (1975-), male, Han ethnicity, from Anqing, Anhui, is a senior engineer with a bachelor's degree. His research interests include thermal power engineering, power generation, and distribution.