Power Quality Disturbance Classification Based on Wave⁃ViT Improved Multi⁃channel Depth Residual Network

LIU Dapeng; LUO Jiabin; LIU Yong; MU Yong; DONG Biao; ZHANG Shuqing

doi:10.3969/j.issn.1000-1158.2025.05.02

PDF(1999 KB)

Acta Metrologica Sinica ›› 2025, Vol. 46 ›› Issue (5) : 629-637. DOI: 10.3969/j.issn.1000-1158.2025.05.02

Power Quality Disturbance Classification Based on Wave⁃ViT Improved Multi⁃channel Depth Residual Network

LIU Dapeng ¹ ,
LUO Jiabin ² ,
LIU Yong ¹ ,
MU Yong ¹ ,
DONG Biao ¹ ,
ZHANG Shuqing ²

Author information +

History +

Abstract

A power quality disturbance classification method based on Wave-ViT improved multi-channel depth residual network is proposed. Firstly， the one-dimensional time series power quality disturbances （PQDS） signal is used as the input of channel one. Then， the one-dimensional PQDS signal is mapped into a two-dimensional image through the Gramian angular field （GAF） as the input of channel two， and the two-dimensional GAF image information is deeply mined by using the wave vision transformer （Wave-ViT） module as the input of channel three， and then the deep feature extraction of the three channels is carried out respectively， and a multi-channel network framework suitable for PQDS classification is constructed. Through ablation experiments， it is confirmed that multi-channel has complementary effect on the convergence speed and classification accuracy of the network. Further noise experiments and comparative experiments show that this method has strong feature extraction ability， less iterations， and good anti noise performance. The recognition rates of 16 kinds of disturbances in random noise and no noise environment can reach 99.81% and 99.19% respectively， which provides a new idea for power quality disturbance recognition.

Key words

electromagnetic metrology / power quality disturbance / Wave-ViT / depth residual network / ablation experiment / noise experiment / disturbance identification

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LIU Dapeng , LUO Jiabin , LIU Yong , et al . Power Quality Disturbance Classification Based on Wave⁃ViT Improved Multi⁃channel Depth Residual Network[J]. Acta Metrologica Sinica. 2025, 46(5): 629-637 https://doi.org/10.3969/j.issn.1000-1158.2025.05.02

References

List( Publishing order | Descend order by publishing year | Descend order by cited within ) Chart analysis

黄雨涵，丁涛，李雨婷，等. 碳中和背景下能源低碳化技术综述及对新型电力系统发展的启示［J］. 中国电机工程学报， 2021， 41（S1）： 28-51.

HUANG

Y H

， DING

， LI

Y T

， et al. Decarbonization Technologies and Inspirations for the Development of Novel Power Systems in the Context of Carbon Neutrality［J］. Proceedings of the CSEE， 2021， 41（S1）： 28-51.

Cited in this article [1]

2	文云峰，杨游航，邢鹏翔，等. 多维因素制约下新能源消纳能力评估方法研究综述［J］. 中国电机工程学报， 2024， 44（1）： 127-147. WEN Y F， YANG Y H， XING P X， et al. Review on the New Energy Accommodation Capability Evaluation Methods Considering Multi-dimensional Factors［J］. Proceedings of the CSEE， 2024， 44（1）： 127-147. Cited in this article [1]

3	汪飞，全晓庆，任林涛. 电能质量扰动检测与识别方法研究综述［J］. 中国电机工程学报， 2021， 41（12）： 4104-4121. WANG F， QUAN X Q， REN L T. Review of Power Quality Disturbance Detection and Identification Methods［J］.Proceedings of the CSEE， 2021， 41（12）： 4104-4121. Cited in this article [1]

4	IGUAL R， MEDRANO C. Research challenges in real-time classification of power quality disturbances applicable to microgrids： A systematic review［J］. Renewable and Sustaina-ble Energy Reviews， 2020， 132： 110050. Cited in this article [1]

5	TONG Z， ZHONG J， LI J， et al. A power quality disturbances classification method based on multi-modal parallel feature extraction［J］. Scientific Reports， 2023， 13（1）： 17655. Cited in this article [1]

6	刘斌，曲丽萍，崔文超，等. 基于改进HHT+WT复合特征提取的电能质量扰动识别方法［J］. 北华大学学报（自然科学版）， 2023， 24（5）： 678-686. LIU B， QU L P， CUI W C， et al. Power Quality Disturbance Identification Method Basedon HHT+WT Composite Feature Extraction［J］.Journal of Bneihua University（Natural Science）， 2023， 24（5）： 678-686.

7	CHAKRAVORTI T， DASH P K. Multiclass power quality events classification using variational mode decomposition with fast reduced kernel extreme learning machine-based feature selection［J］. IET Science， Measurement&Technology， 2018， 12（1）： 106-117. Cited in this article [1]

张淑清，张赟，刘海涛，等. 多重分形去趋势波动分析及改进决策树在电能质量分析中的应用［J］.计量学报， 2021， 42（4）： 424-431.

ZHANG

S Q

， ZHANG

， LIU

H T

， et al. Application in Power Quality Analysis Based on Multifractal Detrended Fluctuation Analysis and lmproved Decision Tree［J］. Acta Metrologica Sinica， 2021， 42（4）： 424-431.

Cited in this article [1]

9	刘海涛，武祥，张淑清，等. 基于优化广义S变换和混合输入神经网络的电能质量扰动识别［J］. 计量学报， 2025， 46（1）： 53-61. LIU H T， WU Xi， ZHANG S Q， et al. Power Quality Disturbance Identification Based on Optimized Generalized S⁃transform and Hybrid Input Neural Network［J］. Acta Metrologica Sinica， 2025， 46（1）： 53-61.

10	吴怀诚，刘家强，岳蕾，等. 基于多特征融合的卷积神经网络的电能质量扰动识别方法［J］. 电网与清洁能源， 2023， 39（9）： 19-23+31. WU H C， LIU J Q， YUE L， et al. Identification of Power Quality Disturbances Based on MFCNN［J］. Power System and Clean Energy， 2023， 39（9）： 19-23+31.

11	MEMON A A， CHANNA I A， ALI I， et al. Power Quality Disturbances （PQDs） Classification Analyzed Based on Deep Learning Technique［J］. Journal of Computing & Biomedical Informatics， 2022， 4（1）： 92-103.

12	MA J， LIU J， QIU W， et al. An intelligent classification framework for complex PQDs using optimized KS-transform and multiple fusion CNN［J］. IEEE Transactions on Industrial Informatics， 2023， 20（2）： 1776-1785.

13	赵晨. 基于极限学习机的电能质量复合扰动分类方法研究［D］. 武汉：华中科技大学， 2019. Cited in this article [1]

14	MEENA H， MEENA H K， SAXENA D. Classification of power quality disturbances with DWT based effective feature extraction［C］// IEEE. 2021 4th International Conference on Recent Trends in Computer Science and Technology （ICRTCST）. 2022： 314-320. Cited in this article [1]

15	肖思丽，胡洁，李建宁. 基于小波变换的电能质量检测与分析［J］. 电力与能源， 2018， 39（2）： 181-185. XIAO S L， HU J， LI J N. Detection and Analysis of Power Quality Based on Wavelet Transform［J］. Power & Energy， 2018， 39（2）： 181-185. Cited in this article [1]

16	CHEN S， LI Z， PAN G， et al. Power Quality Disturbance Recognition Using Empirical Wavelet Transform and Feature Selection［J］. Electronics， 2022， 11（2）： 174. Cited in this article [1]

17	CHAMCHUEN S， SIRITARATIWAT A， FUANGFOO P， et al. High-Accuracy power quality disturbance classification using the adaptive ABC-PSO as optimal feature selection algorithm［J］. Energies， 2021， 14（5）： 1238. Cited in this article [1]

18	郑炜，林瑞全，王俊，等. 基于GAF与卷积神经网络的电能质量扰动分类［J］. 电力系统保护与控制， 2021， 49（11）： 97-104. ZHENG W， LIN R Q， WANG J， et al. Power quality disturbance classification based on GAF and a convolutional neural network［J］. Power System Protection and Control， 2021， 49（11）： 97-104. Cited in this article [1]

19	MACHLEV R， CHACHKES A， BELIKOV J， et al. Open source dataset generator for power quality disturbances with deep-learning reference classifiers［J］. Electric Power Systems Research， 2021， 195： 107-152. Cited in this article [1]

20	贺才郡，李开成，杨王旺，等. 基于双通道GAF和深度残差网络的电能质量复合扰动识别［J］. 电网技术， 2023， 47（1）： 369-379. HE C J， LI K C， YANG W W， et al. Power Quality Compound Disturbance Identification Based on Dual Channel GAF and Depth Residual Network［J］. Power System Technology， 2023， 47（1）： 369-379. Cited in this article [1]

21	YAO T， PAN Y， LI Y， et al. Wave-vit： Unifying wavelet and transformers for visual representation learning［C］//European Conference on Computer Vision. Doi： 10.48550/arXiv.2207.04978 . Cited in this article [1]

22	SINDI H， NOUR M， RAWA M， et al. A novel hybrid deep learning approach including combination of 1D power signals and 2D signal images for power quality disturbance classification［J］. Expert Systems with Applications， 2021， 174： 114785. Cited in this article [1]

23	季佳伸，吴俊勇，王彦博，等. 基于深度残差网络的电力系统暂态电压稳定评估［J］. 电网技术， 2022， 46（7）： 2500-2511. JI J S， WU J Y， WANG Y B， et al. Power System Transient Voltage Stability Assessment Based on Deep Residual Network［J］. Power System Technology， 2022， 46（7）： 2500-2511. Cited in this article [1]

罗溢，李开成，肖贤贵，等. 基于马尔可夫转移场和深度残差网络的电能质量复合扰动多标签分类［J］. 中国电机工程学报， 2024， 44（7）： 2519-2531.

LUO

， LI

K C

， XIAO

X G

， et al. Multi label classification of power quality composite disturbances based on Markov transfer field and deep residual network ［J］. Proceedings of the CSEE， 2024，44（7）： 2519-2531.

Cited in this article [1]