摘要
以提升电能表运行误差计算准确率为目的,提出基于人工智能的电能表运行误差监测数据拟合方法。首先对总电能表与分电能表用电量进行分析,得到电能表运行误差,将误差输入至神经网络实行在线学习,拟合电能表计量值,然后采用萤火虫算法优化神经网络参数,以提高电能表运行误差监测数据动态拟合效果,最后实验结果表明,在不同电网负载以及不同磁波干扰下,该文方法可以高精度拟合电能表运行误差,具有一定的实际应用价值。
In order to improve the accuracy of watt hour meter operation error calculation,an artificial intelligence based data fitting method for watt hour meter operation error monitoring is proposed.Firstly,the total energy meter and the sub meter power consumption are analyzed to get the operation error of the watt hour meter.The error is input into the neural network for online learning to fit the measured value of the electric energy meter.Then,the firefly algorithm is used to optimize the parameters of the neural network to improve the dynamic fitting effect of the monitoring data of the operation error of the watt hour meter.Finally,the experimental results show that:under different grid loads and different magnetic fields Under wave interference,this method can fit the operation error of watt hour meter with high precision,and has certain practical application value.
作者
周玉
邵雪松
马云龙
季欣荣
蔡奇新
ZHOU Yu;SHAO Xue-song;MA Yun-long;JI Xin-rong;CAI Qi-xin(State Grid Jiangsu Marketing Service Center,Nanjing 210019,China;State Grid Jiangsu Electric Power Co.,Ltd.,Nanjing 210024,China)
出处
《自动化与仪表》
2021年第5期75-78,83,共5页
Automation & Instrumentation
关键词
人工智能
电能表
运行误差
数据拟合
计量误差
阈值
误差分析模型
萤火虫算法
artificial intelligence
watt-hour meter
operation error
data fitting
measurement error
the threshold value
error analysis model
firefly algorithm