基于改进随机森林算法的中低压直流配电网剩余电流保护方法  

Residual Current Protection Method for Medium and Low Voltage DC Distribution Network Based on Improved Random Forest Algorithm

在线阅读下载全文

作  者:常潇 郭伟东[2] 李胜文 刘翼肇 杨洋 CHANG Xiao;GUO Weidong;LI Shengwen;LIU Yizhao;YANG Yang(Electric Power Research Institute of State Grid Shanxi Electric Power Company,Taiyuan Shanxi 030001,China;State Grid Shanxi Electric Power Company,Taiyuan Shanxi 030021,China)

机构地区:[1]国网山西省电力公司电力科学研究院,山西太原030001 [2]国网山西省电力公司,山西太原030021

出  处:《电子器件》2024年第6期1625-1632,共8页Chinese Journal of Electron Devices

基  金:国网山西省电力公司科技项目(520530200014)。

摘  要:为解决中低压直流配电网剩余电流造成触电和电气火灾的问题,提出一种基于改进随机森林算法的剩余电流保护方法。利用监控终端实时采集节点剩余电流幅值信息,配合工作站后端计算机采用改进的随机森林算法对剩余电流进行检测并控制断路器排除故障。利用MATLAB软件构建研究对象模型,结果表明,剩余电流故障检测结果的准确率和召回率可以保持在97%以上。针对保护问题,采用分励脱扣器配合微断的方式,实现低压直流剩余电流的保护,并设计了中压适用的混合式断路器。测试表明所提方法具有良好的保护性能,对不同类型的剩余电流故障具有良好的判别能力。In order to solve the problem of electric shock and electrical fire caused by residual current, a protection method based on improved random forest algorithm for medium and low voltage DC distribution network is proposed. Real-time residual current amplitude data of nodes are collected by the intelligent monitoring terminals and transmitted to the workstation backend. The improved random forest algorithm is used to detect the residual current and control the circuit breaker to eliminate the fault. A research object model is constructed by using MATLAB software, and the results show that the accuracy and recall of fault detection results can be maintained at over 97%. The protection of low-voltage DC residual current is realized by means of shunt release and micro-break, and a hybrid circuit breaker suitable for medium voltage is designed.The test shows a good discrimination of different types of residual current faults.

关 键 词:随机森林算法 直流配电网 剩余电流保护 电流振幅信息 断路器 

分 类 号:TM712[电气工程—电力系统及自动化] TP181[自动化与计算机技术—控制理论与控制工程]

 

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