5G通信环境下基于注意力机制的配电网单相接地故障选线技术  被引量:2

Single-phase ground fault line selection technology of distribution network based onattention mechanism in 5Gcommunication environment

在线阅读下载全文

作  者:卢杰 佘强 汪正森 汪海啸 马银库 LU Jie;SHE Qiang;WANG Zhengsen;WANG Tsunami;MA Yinku(State Grid Xining Power Supply Company,Xining 810003,China)

机构地区:[1]国网西宁供电公司,青海西宁810003

出  处:《长江信息通信》2024年第2期176-178,共3页Changjiang Information & Communications

摘  要:由于传统技术在配电网单相接地故障选线中应用效果不佳,不仅选线正确率比较低,而且选线耗时比较长,无法达到预期的故障选线效果,为此提出5G通信环境下基于注意力机制的配电网单相接地故障选线技术。在5G通信环境下利用信号感知器拾取配电网线路暂态量信号,并对感知信号双边滤波处理,通过对暂态量信号S变换,提取到配电网线路故障信号时频特征,利用注意力机制选择单相接地故障线路,以此完成5G通信环境下基于注意力机制的配电网单相接地故障选线。经实验证明,设计技术选线正确率在95%以上,选线耗时在1s以内,在配电网单相接地故障选线方面具有良好的应用前景。Due to the poor application effect of traditional technology in single-phase ground fault line distribution network,not only the accuracy of line selection is relatively low,but also the line selection time is relatively long,which cannot achieve the expected fault line selection effect.Therefore,the single-phase ground fault line distribution technology based on attention mechanism in 5Gcommunication environment is proposed.In 5Gcommunication environment using signal sensor to pick up distribution network line transient signal,and the perception signal bilateral filtering processing,through the transient signal S transformation,extract the distribution network line fault signal time frequency characteristics,using attention mechanism to select single-phase ground fault line,to complete the 5Gcommunication environment based on attention mechanism of distribution network single-phase ground fault line selection.The experiment proved that the accuracy rate of line selection in the design technology is more than 95%,and the line selection time is less than 1s,which has a good application prospect in the single-phase fault distribution network.

关 键 词:5G通信环境 注意力机制 单相接地故障 时频特征 双边滤波 S变换 

分 类 号:TM71[电气工程—电力系统及自动化]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象