基于时频图和时序特征组合的电能质量复合扰动识别

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (5463 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract To address the challenge of identifying power quality disturbances (PQDs), this paper proposes a lightweight two-branch multimodal fusion recognition model, LIRC-BiLSTM. The model first applies an S transform to the raw PQD signals to produce time-frequency images that are fed to a convolutional block attention module (CBAM) branch, while the raw one-dimensional PQD time series vectors are sent to a bidirectional long short-term memory network (BiLSTM) branch. In the CBAM branch, a multi-scale feature-extraction module captures image features at different resolutions, and a CBAM is introduced to adaptively enhance channel and spatial attention, focusing on key patterns and overall trends in the time-frequency images. In the BiLSTM branch, the time-series matrix undergoes lightweight convolutional preprocessing before being input to a BiLSTM, and a self-attention mechanism is applied to strengthen the temporal features. Finally, the outputs of both branches are fused to combine time-frequency and temporal features for PQDs type classification. Simulation results show that the proposed LIRC-BiLSTM model effectively integrates time-frequency images with temporal detail, significantly improving classification accuracy and noise robustness for multiple classes of power quality disturbances.

Key words： power quality disturbances S transform multimodal feature fusion deep learning

Received: 11 August 2025

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	BI Guihong
	SINN SIN
	CHEN Shilong
	ZHANG Wei
	CHEN Shike

Cite this article:

BI Guihong,SINN SIN,CHEN Shilong等. Power quality composite disturbance identification based on combination of time-frequency diagram and timing features[J]. Electrical Engineering, 2026, 27(1): 9-19.

URL:

https://dqjs.cesmedia.cn/EN/Y2026/V27/I1/9

[1] 李云峰, 高云鹏, 蔡星月, 等. 自适应辛几何模态分解和短时能量差分因子在电能质量扰动检测中的应用[J]. 电工技术学报, 2022, 37(17): 4390-4400.
[2] 刘伟, 王凯. 基于通道选择多尺度融合深度残差网络的电能质量扰动识别[J]. 电气技术, 2023, 24(5): 11-15, 22.
[3] 罗斌, 王慧芳, 倪旭明, 等. 基于1D-YOLO网络的电能质量复合扰动检测分类和时间定位模型[J]. 电力自动化设备, 2025, 45(6): 182-190.
[4] 王立辉, 柯泳, 苏如开. 基于1DCNN-BiLSTM- BiGRU的电能质量扰动分类方法[J]. 电气技术, 2024, 25(5): 51-56, 64.
[5] 王义国, 林峰, 李琦, 等. 基于TCN-LSTM模型的电网电能质量扰动分类研究[J]. 电力系统保护与控制, 2024, 52(17): 161-167.
[6] ANGGRIAWAN D O, WAHJONO E, SUDIHARTO I, et al.Identification of short duration voltage variations based on short time Fourier transform and artificial neural network[C]//2020 International Electronics Symposium (IES), Surabaya, Indonesia, 2020: 43-47.
[7] HONG Wenhui, LIU Ziwen, WU Xuyan.Power quality disturbance recognition based on wavelet transform and convolutional neural network[C]//2021 IEEE International Conference on Artificial Intel- ligence and Computer Applications (ICAICA), Dalian, China, 2021: 193-197.
[8] LIANG Chengbin, TENG Zhaosheng, LI Jianmin, et al.A Kaiser window-based S-transform for time- frequency analysis of power quality signals[J]. IEEE Transactions on Industrial Informatics, 2022, 18(2): 965-975.
[9] 黄南天, 彭华, 蔡国伟, 等. 电能质量复合扰动特征选择与最优决策树构建[J]. 中国电机工程学报, 2017, 37(3): 776-786.
[10] LIU Zhigang, CUI Yan, LI Wenhui.A classification method for complex power quality disturbances using EEMD and rank wavelet SVM[J]. IEEE Transactions on Smart Grid, 2015, 6(4): 1678-1685.
[11] 王守相, 李慧强, 赵倩宇, 等. 基于时序二维变换和多尺度Transformer的电能质量扰动分类方法[J]. 电力系统自动化, 2025, 49(7): 198-207.
[12] 黄建明, 瞿合祚, 李晓明. 基于短时傅里叶变换及其谱峭度的电能质量混合扰动分类[J]. 电网技术, 2016, 40(10): 3184-3191.
[13] SAHU G, DASH S, BISWAL B.Time-frequency analysis of power quality disturbances using syn- chroextracting transform[J]. International Transactions on Electrical Energy Systems, 2020, 30(4): e12278.
[14] ENSHAEE A, ENSHAEE P.A new S-transform-based method for identification of power quality dis- turbances[J]. Arabian Journal for Science and Engin- eering, 2018, 43(6): 2817-2832.
[15] 毕贵红, 鲍童语, 陈臣鹏, 等. 基于混合分解多尺度时频图和Res-GRU-AT的电能质量复合扰动识别[J]. 电力系统保护与控制, 2024, 52(4): 12-25.
[16] 张玺, 郑建勇, 梅飞, 等. 基于Lissajous轨迹的电能质量扰动边-云协同高效辨识框架[J]. 电力系统自动化, 2024, 48(22): 210-223.
[17] LI Taifeng, GAO Zhijie, LI Yifan, et al.A com- prehensive study of fast Fourier transform for bearing fault diagnosis with long short-term memory net- works[C]//2023 3rd International Conference on Electrical Engineering and Mechatronics Technology (ICEEMT), Nanjing, China, 2023: 876-879.
[18] 吴建章, 梅飞, 郑建勇, 等. 基于改进经验小波变换和XGBoost的电能质量复合扰动分类[J]. 电工技术学报, 2022, 37(1): 232-243, 253.
[19] 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.
[20] 黄杰, 李建闽, 朱冰凡, 等. 基于条件网络和知识注入的多标签学习电能质量扰动识别与分类方法[J]. 电工技术学报, 2025, 40(23): 7652-7663.
[21] TONG Zhanbei, ZHONG Jianwei, LI Jiajun, et al.A power quality disturbances classification method based on multi-modal parallel feature extraction[J]. Scientific Reports, 2023, 13: 17655.
[22] Recommended practice for monitoring electric power quality: IEEE1159: 2019[S].
[23] STOCKWELL R G, MANSINHA L, LOWE R P.Localization of the complex spectrum: the S trans- form[J]. IEEE Transactions on Signal Processing, 1996, 44(4): 998-1001.
[24] 胡从强, 曲娜, 张帅, 等. 连续小波变换和具有注意力机制的深度残差收缩网络在低压串联电弧故障检测中的应用[J]. 电网技术, 2023, 47(5): 1897-1905.
[25] 李宗源, 陈谦, 钱倍奇, 等. 基于格拉姆角场与并行CNN的并网逆变器开关管健康诊断[J]. 电力自动化设备, 2024, 44(8): 153-159.
[26] 金星, 周凯翔, 于海洲, 等. 基于卷积神经网络与Transformer的电能质量扰动分类方法[J]. 科学技术与工程, 2024, 24(16): 6726-6733.
[27] 王守相, 李慧强, 赵倩宇, 等. 基于时序二维变换和多尺度Transformer的电能质量扰动分类方法[J]. 电力系统自动化, 2025, 49(7): 198-207.
[28] 兰名扬, 刘宇龙, 金涛, 等. 基于可视化轨迹圆和ResNet18的复合电能质量扰动类型识别[J]. 中国电机工程学报, 2022, 42(17): 6274-6286.