摘要
供电系统是煤矿安全生产的基础,变电所的智能化升级是煤矿智能化过程中不可忽视的环节,电力巡检机器人是改变变电所运维检修创新发展模式的重要装备。针对煤矿变电所既有设备实际情况,采用对称特性识别指针类仪表设备的实现方法,分析了巡检机器人所需巡检的设备类型及其重要特征;采用AlexNet卷积神经网络技术识别数字类仪表设备的实现方法,研究了采用自适应二值化和偏转角度计算理论识别电气和机械状态指示类仪表设备的实现方式,对局部放电检测方法进行了理论分析。通过对变电所主要仪表和设备类型识别方法的研究,构成了完整的电力巡检机器人整体识别方案,提高了巡检机器人作业效率和巡检质量,提升了变电所运维检修能力。
The power supply system is the basis of coal mine safety production.The intelligent upgrading of substation is a link that can not be ignored in the intelligent process of coal mine.The power inspection robot is an important equipment to change the innovative development mode of substation operation and maintenance.According to the actual situation of existing equipment in coal mine substation,the implementation method of identifying pointer instrument equipment with symmetrical characteristics is adopted,and the types and important characteristics of inspection equipment required by inspection robot are analyzed.The realization method of identifying digital instrument equipment by using alexnet convolution neural network technology is studied.The realization method of identifying electrical and mechanical state indication instrument equipment by using adaptive binarization and deflection angle calculation theory is studied,and the partial discharge detection method is analyzed theoretically.Through the research on the identification method of the main instruments and equipment types of the substation,a complete overall identification scheme of the power inspection robot is formed,which improves the operation efficiency and inspection quality of the inspection robot,and improves the operation and maintenance ability of the substation.
作者
宋国栋
SONG Guo-dong(Information Research Institute of the Ministry of Emergency Management,Beijing 100029,China)
出处
《煤炭科技》
2022年第1期100-104,共5页
Coal Science & Technology Magazine
基金
国家国际科技合作项目(2014DFR70500)
应急管理部信息研究院科技创新发展基金(CX2019001)。
关键词
煤矿电力
巡检机器人
对称特性
神经网络
自适应二值化
coal mine electric power
inspection robot
symmetry characteristic
neural network
adaptive binarization
