摘要
针对电力通信光缆线路在复杂环境下难以实现弧垂实时精确测量问题,提出了一种基于参数优选的光缆弧垂预测方法。首先,采用倾角-弧垂计算模型拟合光缆弧垂曲线;其次,使用麻雀搜索算法优化的BP神经网络对弧垂误差进行估计以实现非线性修正;最后,结合理论值和修正值实现电力通信光缆弧垂的精确测量。同时,为提升BP神经网络的性能,利用Choquet积分评估环境参数和光缆参数对弧垂的影响,筛选出重要的特征参数作为BP神经网络的输入。实验结果表明:采用所提出方法预测光缆弧垂平均相对误差δ在3%以内,大幅提高了预测精度。
Aiming to the difficulty of achieving real-time and accurate measurement of sag in complex environments for power communication optical cable lines,an optical cable sag prediction method is proposed based on parameter optimization.Firstly,the optical cable sag curve is fit by using inclination-sag calculation model.Secondly,sag error is estimated based on BP neural network optimized by sparrow search algorithm(SSA)to achieve nonlinear correction.Finally,the theoretical value and the corrected value are combined to realize the sag accurate measurement of the power communication optical cable.At the same time,in order to improve the performance of the BP neural network,the Choquet integral is used to evaluate the influence of environmental parameters and optical cable parameters on the sag,and the important characteristic parameters are selected as the input of the BP neural network.The experimental results show that the mean relative error δ of the optical cable sag predicted by the proposed method is within 3%and the prediction accuracy is effectively improved.
作者
蒋陵
王驭扬
张灿
管翰林
魏鹏超
焦良葆
温秀兰
JIANG Ling;WANG Yuyang;ZHANG Can;GUAN Hanlin;WEI Pengchao;JIAO Liangbao;WEN Xiulan(Information and Telecommunication Branch,State Grid Jiangsu Electric Co.Ltd,Nanjing Power Supply Company,Nanjing,Jiangsu 210019,China;AI Industrial Technology Research Institute,Nanjing Institute of Technology,Nanjing,Jiangsu 211167,China)
出处
《计量学报》
北大核心
2025年第9期1307-1314,共8页
Acta Metrologica Sinica
基金
国网江苏省电力有限公司科技项目(J2023074)。
关键词
几何量计量
电力通信光缆
弧垂预测
倾角传感器
麻雀搜索算法
BP神经网络
geometrical metrology
power communication fiber optic cables
sag prediction measurement
inclination sensor
sparrow search algorithm
BP neural network
