| 引用本文: | 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.[点击复制] |
| BI Guihong,BAO Tongyu,CHEN Chenpeng,et al.Composite PQDs identification based on a hybrid decomposition multi-scale time-frequencymap and Res-GRU-AT[J].Power System Protection and Control,2024,52(4):12-25[点击复制] |
|
| 摘要: |
| 能源互联网背景下的电能质量问题越来越凸显，针对传统电能质量扰动(power quality disturbances, PQDs)识别过程中存在的信号特征提取复杂、算法识别能力不足和复合扰动区分困难等问题，提出了一种混合分量多尺度时频图和残差神经网络(residual neural network, ResNet)、门控循环单元(gated recurrent units, GRU)网络与注意力机制(attention, AT)组合的电能质量复合扰动识别新方法—Res-GRU-AT。首先利用奇异谱分解(singular spectrum decomposition, SSD)和逐次变分模态分解(successive variational mode decomposition, SVMD)对PQDs信号分别进行多尺度分解得到混合分量，再对混合分量进行希尔伯特黄变换(Hilbert-Huang transform, HHT)，分析得到多尺度时频图。其次，利用Res-GRU-AT模型对多尺度时频图进行深层次特征提取、强化和识别。Res-GRU-AT模型能够利用ResNet的二维图像空间特征提取能力和GRU的时序特征提取能力进行特征融合，再通过AT进行特征加权强化，提高了PQDs的识别能力。不同方案的仿真结果表明，所提方法特征提取能力强且抗噪性能好，对复合扰动识别率高。 |
| 关键词: 电能质量 故障识别 时频分析 混合模式分解 深度学习 |
| DOI：10.19783/j.cnki.pspc.230241 |
| 投稿时间：2023-03-10修订日期：2023-12-31 |
| 基金项目:国家自然科学基金项目资助(51767012) |
|
| Composite PQDs identification based on a hybrid decomposition multi-scale time-frequencymap and Res-GRU-AT |
| BI Guihong,BAO Tongyu,CHEN Chenpeng,ZHAO Sihong,CHEN Shilong,ZHANG Zirui |
| (School of Electric Power Engineering, Kunming University of Science and Technology, Kunming 650500, China) |
| Abstract: |
| The power quality problem in the context of the energy internet is becoming more and more prominent. However, there are several problems in the traditional power quality disturbance (PQD) identification process, such as the signal feature extraction is complex, the algorithm recognition ability is insufficient, and it is difficult to differentiate composite disturbance, etc. Thus a new method—Res-GRU-AT, combining hybrid component multi-scale time-frequency diagram, residual neural network (ResNet), gated recurrent units (GRU) network and attention (AT) mechanism, is proposed for power quality composite disturbance identification. First, the PQDs signals are decomposed at multiple scales using singular spectrum decomposition (SSD) and successive variational modal decomposition (SVMD) respectively to obtain the hybrid components. Then the hybrid components are analyzed by Hilbert-Huang transform (HHT) to obtain the multi-scale time-frequency diagram. Secondly, multi-scale time-frequency diagrams are deeply extracted, strengthened, and recognized using the Res-GRU-AT model. The Res-GRU-AT model can perform feature fusion by using the spatial feature extraction capability for 2D images of ResNet and the temporal feature extraction capability of GRU. Then the feature-weighted enhancement is done by AT to improve the recognition capability of PQDs. Simulation results of different schemes show that the proposed method has strong feature extraction capability, good noise immunity, and high recognition rate of composite perturbation. |
| Key words: power quality fault identification time and frequency analysis, hybrid decomposition deep learning |
