摘要
地下变电站环境复杂,电气设备、障碍物和墙壁较多,传统的室内定位系统定位精度较低,无法满足日常工作的需求。为此文章提出了一种基于超宽带的查恩–高斯牛顿迭代–反向传播神经网络(Chan-Gauss Newton-Back Propagation Neural Network,CGN-BPNN)的非视距误差抑制算法,首先利用Chan算法得出的坐标作为高斯牛顿迭代算法初始值进行迭代,并对算法所得的残差进行加权,使离标签越近的基站测得数据的权重提高,然后将迭代后得到的坐标值作为训练完毕的误差反向传播(Back Propagation,BP)神经网络的输入进行修正,输出即为最终的定位结果。计算机仿真结果表明该算法定位精度相较传统的Chan算法提升了42.9%,相较Chan-Gauss Newton算法提升21.9%,研究结果对于超宽带(Ultra Wide Band,UWB)技术在地下变电站中的应用具有广泛而积极的意义。
The underground substation environment is complex,with many electrical equipments,obstacles and walls.The traditional indoor positioning system has low positioning accuracy and cannot meet the needs of daily work.To solve the problem,this paper proposes a non-line-of-sight error suppression algorithm based on the ultra-wideband-Chan-Gauss-Newton iterative-BP neural network(Chan Gauss Newton-BPNN,CGN-BPNN).First,the coordinates obtained by the Chan algorithm are used as the initial values of the Gauss-Newton iterative algorithm to iterate,and the residuals of the algorithm obtained are weighted to increase the weight of the measured data of the base station closer to the label,and then the coordinate value obtained after the iteration is used as the input of the trained BP neural network for correction,and the output is the final positioning result.Computer simulation results show that the positioning accuracy of this algorithm is improved by 42.9%compared with the traditional Chan algorithm,and by 21.9%compared with the Chan Gauss Newton algorithm,which has a wide and positive significance for the application of UWB technology in underground substations.
作者
潘海瑞
刘传清
韦朴
周康
袁航
PAN Hairui;LIU Chuanqing;WEI Pu;ZHOU Kang;YUAN Hang(School of Electric Power,Nanjing Institute of Technology,Nanjing 211100,China;Institute of Information and communication,Nanjing Institute of Technology,Nanjing 211100,China)
出处
《电力信息与通信技术》
2021年第5期82-88,共7页
Electric Power Information and Communication Technology
关键词
地下变电站
UWB定位
神经网络
高斯牛顿迭代
underground substation
UWB positioning
neural network
Gauss Newton iteration
作者简介
通信作者:潘海瑞(1996-),男,硕士研究生,研究方向为UWB定位在变电站中的应用,1415787074@qq.com;刘传清(1964-),男,教授,研究方向为智能电网信息技术、物联网技术;韦朴(1981-),男,副教授,研究方向为物联网技术;周康(1995-),男,硕士研究生,研究方向为激光供能技术;袁航(1998-),男,硕士研究生,研究方向为物联网技术。
