电缆廊道和管孔图纸综合运维管控系统设计  被引量:1

Design of Integrated Operation and Maintenance Management and Control System for Cable Corridor and Pipe Hole Drawings

在线阅读下载全文

作  者:杨立明 周浩亮 戴林 Yang Liming;Zhou Haoliang;Dai Lin(State Grid Zhejiang Yuyao Power Supply Co.,Ltd.,Yuyao Zhejiang 315400,China)

机构地区:[1]国网浙江余姚市供电有限公司,浙江余姚315400

出  处:《电气自动化》2022年第2期65-67,71,共4页Electrical Automation

摘  要:针对目前管廊运维管控系统性能差、数据处理效率低的问题,研究出一套适用的解决方案。采用了基于随机矩阵理论的数据校核模型来分析地下通道中电缆廊道和管孔图纸数据,能够及时、准确地处理数据信息。将正常和异常监视视频视为袋子,并将电缆廊道监测数据视为袋子中的实例,利用分类中性能指标AUC来预测异常监测数据。结果表明,提出的方法比其他方法的误差要低得多,数据校核算法误差<12%,AUC最低为3.9%,验证了所用方法的适用性与可靠性。Aiming at the problems of poor performance and low data processing efficiency of the current pipeline gallery operation and maintenance management system,a set of suitable solutions was developed.A data check model based on random matrix theory was used to analyze the drawing data of cable corridors and pipe holes in underground passages,which can process data information in a timely and accurate manner.The normal and abnormal monitoring videos were regarded as bags and the cable corridor monitoring data as instances in the bags,and the abnormal monitoring data was predicted by the performance index AUC in the classification.The test results show that the error of the proposed method is much lower than other methods.The error of the data checking algorithm is less than 12%,and the minimum AUC is 3.9%,which verifies the applicability and reliability of the method used in this study.

关 键 词:电缆廊道 智能运维 数据校核算法 多实例学习 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

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