| 引用本文: | 武霁阳,李 强,陈 潜,等.知识图谱框架下基于深度学习的HVDC系统故障辨识[J].电力系统保护与控制,2023,51(20):160-169.[点击复制] |
| WU Jiyang,LI Qiang,CHEN Qian,et al.Fault identification of an HVDC system based on deep learning in the framework of a knowledge graph[J].Power System Protection and Control,2023,51(20):160-169[点击复制] |
|
| 摘要: |
| 为加快电力系统数字化转型，保证高压直流输电(high voltage direct current, HVDC)系统高质量安全运行，有必要通过智能技术充分挖掘、提炼HVDC系统日常调控、运维等阶段积累的海量数据和丰富管理经验，从而构建知识图谱辅助工作人员对故障进行诊断和处理。提出了一种基于小波变换和深度学习的HVDC系统故障诊断方法。首先，采用小波变换将换流站的故障录波数据(单相接地、相间短路和阀组短路)转换为二维时频图像，并采用数据增强技术来进一步扩充样本数据集。然后，利用ResNet50网络来实现HVDC系统的故障诊断。根据实验结果，所提方法在训练集的分类精度为93%，在测试集的分类精度为82%，证明了该方法的有效性，为HVDC系统的故障诊断提供了一种新的可行性路线。为了进一步验证所提方法，将其与GoogleNet、VGG16、AlexNet、SVM、决策树和KNN等方法进行对比，对比实验结果表明，所提方法在HVDC系统故障诊断中的表现更加出色。 |
| 关键词: 高压直流输电系统 故障诊断 小波变换 深度学习 |
| DOI：10.19783/j.cnki.pspc.230082 |
| 投稿时间：2023-01-19修订日期：2023-02-06 |
| 基金项目:国家自然科学基金项目资助(62263014)；南方电网重点科技项目资助(CGYKJXM20210309，CGYKJXM20220343) |
|
| Fault identification of an HVDC system based on deep learning in the framework of a knowledge graph |
| WU Jiyang1,LI Qiang2,CHEN Qian3,QIU Youqiang2,GUO Jianbao1,XIAO Yaohui1 |
| (1. Maintenance and Test Center of CSG EHV Power Transmission Company of China Southern Power Grid Co., Ltd.,
Guangzhou 510000, China; 2. Dali Bureau, EHV Power Transmission Company of China Southern Power
Grid Co., Ltd., Dali 671000, China; 3. EHV Power Transmission Company of China Southern
Power Grid Co., Ltd., Guangzhou 510000, China) |
| Abstract: |
| To accelerate the digital transformation of the power system and ensure the high-quality and safe operation of the high voltage direct current (HVDC) system, it is necessary to fully mine and extract the massive data and rich management experience accumulated in daily regulation, operation and maintenance of such a system through intelligent technologies. Thus, a knowledge map is constructed to assist the staff in diagnosing and dealing with faults. This paper presents a fault diagnosis method for an HVDC system based on wavelet transform and deep learning. First, the fault recording data (single-phase grounding, phase-to-phase short circuit and valve group short circuit) of the converter station is converted into two-dimensional time-frequency images by wavelet transform, and data enhancement technology is used to further expand the sample data set. Then, the ResNet50 network is used to achieve the fault diagnosis of the HVDC system. The results are that the classification accuracy of the proposed method in the training set is 93%, and the classification accuracy of the test set is 82%. This proves the effectiveness of the proposed method and provides a new feasible route for fault diagnosis of the system. To further test the proposed method, it is compared with GoogleNet, VGG16, AlexNet, SVM, decision tree and KNN. The results show that the proposed method performs better in fault diagnosis of the HVDC system. |
| Key words: high voltage direct current transmission system fault diagnosis wavelet transform deep learning |
