| 引用本文: | 何俊涛,车仁飞,孟庆萌,张昊.基于广域录波数据和FCM聚类的电网故障诊断方法[J].电力自动化设备,2019,39(6): |
| HE Juntao,CHE Renfei,MENG Qingmeng,ZHANG Hao.Fault diagnosis method of power grid based on wide-area recorder data and fuzzy C-means clustering[J].Electric Power Automation Equipment,2019,39(6): |
|
| 摘要: |
| 断路器和保护设备存在误动和拒动的可能性，不正确的动作会引入错误的故障信息干扰电网故障诊断。针对上述问题提出了一种基于广域故障录波数据和模糊C均值(FCM)聚类的电网故障诊断方法。对母线、输电线路和变压器这3种电网元件的故障录波数据进行挖掘分析，从中提取能够有效区分故障元件的特征；建立基于模糊C均值聚类的电网故障元件诊断模型。对故障后的元件进行聚类分析，并计算各元件的故障可信度，最终确定故障元件。新英格兰39节点系统的仿真和实际算例表明所提方法能够快速准确定位故障元件且不受故障类型和位置的影响。 |
| 关键词: 电网故障诊断 广域故障录波 模糊C均值分析 小波分析 故障特征 故障可信度 |
| DOI：10.16081/j.issn.1006-6047.2019.06.026 |
| 分类号:TM761 |
| 基金项目: |
|
| Fault diagnosis method of power grid based on wide-area recorder data and fuzzy C-means clustering |
|
HE Juntao, CHE Renfei, MENG Qingmeng, ZHANG Hao
|
|
Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education, Shandong University, Jinan 250061, China
|
| Abstract: |
| There is a possibility of mal-operation and miss-operation of circuit breakers and protection equipment, and improper actions will cause incorrect alarm information and affect fault diagnosis of power grid. A power grid fault diagnosis method based on wide-area fault recording data and FCM(Fuzzy C-Means) clustering is proposed for the above problems. The fault recording data of bus, transmission line and transformer are extracted and analyzed to extract features that can be used to effectively distinguish faulty components. A fault diagnosis model of power grid based on fuzzy C-means clustering is established. The cluster analysis of the components after the grid fault is carried out, and the fault credibility of each component is calculated to determine the fault components. The simulation of the New England 39-bus system and an actual case study show that the proposed method can identify faulty components quickly and correctly, and is immune to fault location and type. |
| Key words: fault diagnosis of power grid wide-area fault recording fuzzy C-means analysis wavelet analysis fault feature fault credibility |
