1.国网信息通信产业集团有限公司,北京 100053
2.国网信通亿力科技有限责任公司,福建 福州 350003
收稿:2026-03-20,
修回:2026-05-11,
录用:2026-06-23,
移动端阅览
孟祥亮, 王利民, 肖新华, 等. 基于时频融合与置信度优化的电能质量复合扰动识别[J/OL]. 电信科学, 2026.
MENG Xiangliang, WANG limin, XIAO xinghua, et al. Recognition of Composite Power Quality Disturbances Based on Time-Frequency Fusion and Confidence Optimization[J/OL]. Telecommunications Science, 2026.
孟祥亮, 王利民, 肖新华, 等. 基于时频融合与置信度优化的电能质量复合扰动识别[J/OL]. 电信科学, 2026. DOI: 10.11959/j.issn.1000-0801.DXKX260186.
MENG Xiangliang, WANG limin, XIAO xinghua, et al. Recognition of Composite Power Quality Disturbances Based on Time-Frequency Fusion and Confidence Optimization[J/OL]. Telecommunications Science, 2026. DOI: 10.11959/j.issn.1000-0801.DXKX260186.
随着新能源发电技术的广泛应用,电网中电能质量扰动(PQD)的类型日益复杂,多重扰动叠加现象频发,传统分类方法因依赖完备训练样本,难以有效识别未见过的复合扰动类型。为此,提出一种基于时频特征融合与置信度优化(time-frequency feature fusion and confidence optimization
TFFF-CO)的电能质量扰动分类方法。首先,对PQD信号进行快速傅里叶变换(FFT)获取频谱信息,利用注意力增强型门控循环单元(AGRU-ATT)提取时域动态特征,采用轻量型多尺度卷积网络(MS-CNN-Lite)捕捉频域局部特征;其次,通过自适应权重分配策略融合时频特征,增强特征表征的完整性与针对性;然后,在多标签学习框架下引入类别区分标签,实现单一与多重扰动的初步划分,并预测各扰动标签的置信度;最后,设计置信度补偿因子,在不影响已知扰动识别精度的前提下,提升未知多重扰动的置信度区分能力。仿真实验表明,该方法仅采用单一和双重扰动样本训练时,对三重、四重扰动的识别准确率分别达到99.42%和96.38%。
With the wide application of new energy power generation technologies
the types of power quality disturbances (PQD) in power grids are becoming increasingly complex
and the phenomenon of multiple disturbances superimposing frequently occurs. Traditional classification methods
which rely on complete training samples
are difficult to effectively identify unseen compound disturbance types. Therefore
a power quality disturbance classification method based on time-frequency feature fusion and confidence optimization (TFFF-CO) is proposed. Firstly
the PQD signal is subjected to fast Fourier transform (FFT) to obtain spectral information
and the time-domain dynamic features are extracted using the attention-enhanced gated recurrent unit (AGRU-ATT)
while the frequency-domain local features are captured by the lightweight multi-scale convolutional neural network (MS-CNN-Lite). Secondly
the time-frequency features are fused through an adaptive weight allocation strategy to enhance the integrity and specificity of feature representation. Then
in the multi-label learning framework
category discrimination labels are introduced to achieve the preliminary division of single and multiple disturbances and predict the confidence of each disturbance label. Finally
a dynamic confidence optimization factor is designed to improve the confidence discrimination ability of unknown multiple disturbances without affecting the recognition accuracy of known disturbances. Simulation experiments show that when this method is trained only with single and double disturbance samples
the recognition accuracy for triple and quadruple disturbances reaches 99.42% and 96.38%
respectively.
黄永红 , 浦骁威 , 张龙 , 等 . 基于MLMD的电能质量扰动检测方法 [J ] . 电测与仪表 , 2024 , 61 ( 5 ): 152 - 159 .
刘海涛 , 张淑清 , 宋珊珊 , 等 . 基于VMD和数据降维的电能质量扰动检测方法 [J ] . 燕山大学学报 , 2023 , 47 ( 2 ): 127 - 136 .
杨岚 , 周国华 , 冯立 , 等 . 基于矩阵式背靠背变换器的统一电能质量控制器补偿策略研究 [J ] . 电气工程学报 , 2025 , 20 ( 05 ): 148 - 158 .
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 ( 05 ): 11 - 15+22 .
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 ( 07 ): 2519 - 2531 .
THIRUMALA K , PAL S , JAIN T , et al . A classification method for multiple power quality disturbances using EWT based adaptive filtering and multiclass SVM [J ] . Neurocomputing , 2019 , 334 : 265 - 274 .
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 .
徐艳春 , 高永康 , 李振兴 , 等 . 基于 VMD 初始化 S 变换的混合动力系统电能质量扰动检测与分类 [J ] . 中国电机工程学报 , 2019 , 39 ( 16 ): 4786 - 4798 .
叶鹏 , 吴浩 , 宋弘 。 基于动态多尺度时频特征互补融合的电能质量扰动分类方法 [J ] . 云南大学学报 (自然科学版) , 2025 , 47 ( 2 ): 1 - 10 .
LI J M , TENG Z S , QIU T , et al . Detection and classification of power quality disturbances using double resolution S-transform and DAG-SVMs [J ] . IEEE Transactions on Instrumentation and Measurement , 2016 , 65 ( 10 ): 2302 - 2312 .
张锐 , 张闯 , 高辉 , 等 . 基于自适应特征增强分组卷积网络的电能质量扰动分类 [J ] . 中国电机工程学报 , 2023 , 43 ( 15 ): 5808 - 5818 .
覃日升 , 徐志 , 况华 , 等 . 基于双分辨率 S 变换和改进的多尺度 ResNet 模型的电能质量扰动检测方法 [J ] . 广东电力 , 2024 , 37 ( 7 ): 68 - 77 .
LUO Y , LI K C , LI Y Z , et al . Three-layer bayesian network for classification of complex power quality disturbances [J ] . IEEE Transactions on Industrial Informatics , 2018 , 14 ( 9 ): 3997 - 4006 .
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 , 4 ( 7 ): 20 - 28 .
胡登宇 , 王宝华 , 刘晋宏 . 基于改进图神经网络的含源配电网故障诊断方法及效果 [J ] . 科学技术与工程 , 2025 , 25 ( 21 ): 8936 - 8944 .
DU Z L , PENG Z , SUN J C , et al . Complex power quality disturbance recognition research based on deep complementary fusion of 2-D coding transition [J ] . IEEE Transactions on Instrumentation and Measurement , 2024 , 73 : 1 - 12 .
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 .
GAO D X , GUAN Y P , LI Y F , et al . A novel label-guided attention method for multilabel classification of multiple power quality disturbances [J ] . IEEE Transactions on Industrial Informatics , 2022 , 18 ( 7 ): 4698 - 4706 .
DENG Y , WANG L , JIA H , et al . A sequence-to-sequence deep learning architecture based on bidirectional GRU for type recognition and time location of combined power quality disturbance [J ] . IEEE Transactions on Industrial Informatics , 2019 , 15 : 4481 - 4493 .
刘大鹏 , 罗嘉宾 , 刘勇 , 等 . 基于Wave-ViT 的改进多通道深度残差网络的电能质量扰动分类 [J ] . 计量学报 , 2025 , 46 ( 5 ): 629 - 637 .
毕贵红 , 杨楠 , 刘大卫 , 等 . 基于时频图像组合和DenseNet-CPSAMs的电能质量复合扰动识别 [J ] . 电力系统保护与控制 , 2025 , 53 ( 17 ): 156 - 168 .
杨惠 , 陈雷 , 徐建军 , 等 . 基于一维残差收缩网络的电能质量复合扰动识别 [J ] . 自动化技术与应用 , 2024 , 43 ( 4 ): 51 - 55 .
刘宇龙 , 崔宪阳 , 袁丁 , 等 . 基于多级注意力机制融合的电能质量扰动点分类及时间定位方法研究 [J ] . 中国电机工程学报 , 2024 , 44 ( 11 ): 4298 - 4310 .
张帅 , 程志友 , 田甜 , 等 . 基于马尔可夫转移场和轻量级网络的非侵入式负荷识别 [J ] . 电力系统保护与控制 , 2024 , 52 ( 17 ): 51 - 61 .
于华楠 , 阮筱颖 , 王鹤 . 基于改进堆叠去噪自动编码器的电能质量扰动分类方法 [J ] . 电力信息与通信技术 , 2021 , 19 ( 09 ): 1 - 7 .
Akkaya S , Sezer Dümen . A novel vision transformer-based power quality disturbance classification method [J ] . Ain Shams Engineering Journal , 2025 , 16 ( 11 ): 103718 - 103726 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621