应用径向基函数神经网络的经纬仪跟踪误差建模

李淼; 高慧斌

doi:10.3788/OPE.20122004.0818

您当前的位置：

首页 >

文章列表页 >

应用径向基函数神经网络的经纬仪跟踪误差建模

信息科学 | 更新时间：2020-08-12

- 应用径向基函数神经网络的经纬仪跟踪误差建模
- Modeling for tracking error of theodolite based on RBF neural network
- 光学精密工程 2012年20卷第4期页码：818-825
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所,吉林长春,中国,130033
  2. 中国科学院研究生院北京,100039
- 作者简介：
- 基金信息：
  
  国家863高技术研究发展计划资助项目(No.2008AA0047)()
- DOI：10.3788/OPE.20122004.0818
  中图分类号： V556;TP183
- 收稿日期：2011-05-04，
  
  修回日期：2011-05-26，
  
  网络出版日期：2012-04-22，
  
  纸质出版日期：2012-04-22
- 稿件说明：
移动端阅览
李淼, 高慧斌. 应用径向基函数神经网络的经纬仪跟踪误差建模[J]. 光学精密工程, 2012,(4): 818-825

LI Miao, GAO Hui-bin. Modeling for tracking error of theodolite based on RBF neural network[J]. Editorial Office of Optics and Precision Engineering, 2012,(4): 818-825
李淼, 高慧斌. 应用径向基函数神经网络的经纬仪跟踪误差建模[J]. 光学精密工程, 2012,(4): 818-825 DOI： 10.3788/OPE.20122004.0818.

LI Miao, GAO Hui-bin. Modeling for tracking error of theodolite based on RBF neural network[J]. Editorial Office of Optics and Precision Engineering, 2012,(4): 818-825 DOI： 10.3788/OPE.20122004.0818.

摘要

提出了一种基于径向基函数(RBF)神经网络建立光电经纬仪等效跟踪误差模型的方法来评价光电经纬仪的跟踪性能。分析了光电经纬仪存在的非线性因素

说明了采用理论建模方法难以准确描述其全部过程的原因。然后

介绍了RBF神经网络和靶标系统

基于一组靶标参数建立了RBF神经网络模型

并更换靶标参数进行模型验证。最后

对更换后的靶标参数进行重新训练建模

并改变参数周期

对模型进行了验证。实验结果表明:所建的神经网络模型精度与靶标参数有关

当动态靶标的半椎角

为21.2

倾角

为43.8

靶标匀速运行周期

为8.5 s时

网络模型在靶标速度最大时误差也达到最大为3.18'

其它时刻均小于0.6'。当

为16.6

为37.5

为13 s时

模型最大误差为1.8'左右

在此模型下真实输出与网络模型输出的最大偏差为2.4'左右

其它时刻均小于1.2'。结果表明

采用RBF神经网络所建立的跟踪误差模型能够反应真实系统的情况

是可行实用的

且具有较高的精度和泛化能力。

Abstract

To effectively evaluate the tracking ability of a photoelectric theodolite

a new tracking error model based on the Radial Basis Function(RBF) neural network was established. First

the nonlinear factors existing in the theodolite were described and the reason why the system was hard to be modeled based on theory was discussed. Then

the RBF neural network theory and the target system were introduced

and the RBF neural network model was built and verified in different parameters. Finally

the network model with new parameters and data was trained and the new network model was obtained through changing parameter periods. Experimental results indicate that the precision of the neural network is closely dependent on the target system parameters. When the half cone angle(

) and the tilt angle(

) of a dynamic target are 21.2? and 43.8?

respectively

and the moving period(

) is 8.5 s

the maximum model error is 3.18' in the acceleration coming to the maximum. And for other time

the model error is less than 0.6'. Furthermore

when the

and

are 16.6?

37.5?

and

is 13 s

the maximum model error is about 1.8'. With the network model

the maximum error between model output and real output is 2.4' in the speed coming to maximum. And for other time

the maximum model error is less than 1.2'. The results indicate that the network model based on RBF neural network can replace a real system in a certain sense. It is feasible and has high accuracy and important value to the engineering practice.

关键词

Keywords

references

赵学颜,李迎春. 靶场光学测量[M]. 北京:国防工业出版社,2001. ZHAO X Y,LI Y CH. Optical Measuring in Shooting Range[M]. Beijing:National Defense Press,2001.(in Chinese)[2] 张宁,沈湘衡,杨亮. 应用跟踪误差等效模型评价光电经纬仪跟踪性能[J]. 光学精密工程,2010,18(3):677-684. ZHANG N, SHEN X H, YANG L. Evaluation of tracking performance of photoelectric theodolite by using equivalent model of tracking error [J]. Opt. Precision Eng., 2010,18(3):677-684.(in Chinese)[3] 张宁,沈湘衡,杨亮,等. 利用动态靶标谐波特性评价光电经纬仪跟踪性能[J]. 光学精密工程,2010,18(6):1286-1294. ZHANG N, SHEN X H, YANG L, et al.. Evaluation of tracking performance of photoelectric theodolite by using harmonic property of dynamic target[J]. Opt. Precision Eng., 2010,18(6):1286-1294.(in Chinese)[4] 李慧,沈湘衡. 光电经纬仪的机电动力学建模与耦合[J]. 光学精密工程,2007,15(10):1577-1582. LI H, SHEN X H. Electromechanical dynamic modeling and coupling for optoelectronic theodolite[J]. Opt. Precision Eng., 2007,15(10):1577-1582.(in Chinese)[5] 王建立,王帅,陈涛,等. 光电跟踪伺服系统的频率特性测试与模型辨识[J]. 光学精密工程,2009,17(1):78-84. WANG J L, WANG SH, CHEN T, et al.. Frequency characteristic test and model identification for O-E tracking servo system[J]. Opt. Precision Eng., 2009,17(1):78-84.(in Chinese)[6] 张斌,李洪文,郭立红,等. 变结构PID在大型望远镜速度控制中的应用[J]. 光学精密工程,2010,18(7):1613-1619. ZHANG B, LI H W, GUO L H, et al.. Application of variable structure PID in velocity control for large telescope[J]. Opt. Precision Eng., 2010,18(7):1613-1619.(in Chinese)[7] 徐春梅. 机械伺服系统基于模糊神经网络的复合控制[J]. 控制工程,2010,17(2):146-148. XU CH M. Complex control based on fuzzy-neural for mechanical servo systems[J]. Control Engineering of China, 2010,17(2):146-148.(in Chinese)[8] DENIS G, KARISHNASWAMY S. Adaptive friction compensation for precision machine tool drives[J]. Control Engineering Practice,2004,12(11):1451-1464.[9] 王俊国. 基于神经网络的建模方法与控制策略研究. 武汉:华中科技大学,2004. WANG J G. Research of modeling methods and control strategies based on neural networks. Wuhan: Huazhong University of Science & Techonology, 2004.(in Chinese)[10] 刘宇. 压电陀螺漂移特性的灰色神经网络建模研究[J]. 系统仿真学报. 2007,19(20):4676-4679. LIU Y. Study on gray neural network drift modeling for piezoelectric gyro[J]. Journal of System Simulation, 2007,19(20):4676-4679.[11] 朱凯. 精通MATLAB神经网络[M]. 北京:电子工业出版社,2010. ZHU K. Master Neural Network with MATLAB [M]. Beijing:Publishing House of Electronics Industry, 2010. (in Chinese)[12] 朱陶业. 光电测量信息中大气折射误差的神经网络建模修正研究. 广州:中南大学,2007. ZHU T Y. Research of the atmospheric refraction errors correction on the neural network in photo-electricity survey information . Guangzhou: Zhongnan Universiy, 2007. (in Chinese)

浏览量

635

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

光电经纬仪脱靶量和坐标动态修正

靶场适用的光电经纬仪光轴平行性检测

卫星激光通信粗跟踪系统复合控制策略

X-Y直线电机精密运动平台的轮廓误差主动补偿