基于改进径向基函数神经网络的激光陀螺温度补偿

史震; 陈帅; 张健; 赵琳; 孙骞

doi:10.3788/OPE.20142211.2975

您当前的位置：

首页 >

文章列表页 >

基于改进径向基函数神经网络的激光陀螺温度补偿

微纳技术与精密机械 | 更新时间：2020-08-13

- 基于改进径向基函数神经网络的激光陀螺温度补偿
- Temperature compensation of laser gyro based on improved RBF neural network
- 光学精密工程 2014年22卷第11期页码：2975-2982
- 作者机构：
  
  哈尔滨工程大学自动化学院,黑龙江哈尔滨,150001
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.61273081)()
- DOI：10.3788/OPE.20142211.2975
  中图分类号： TH824.3;TP183
- 收稿日期：2013-12-18，
  
  修回日期：2014-02-27，
  
  纸质出版日期：2014-11-25
- 稿件说明：
移动端阅览
史震, 陈帅, 张健等. 基于改进径向基函数神经网络的激光陀螺温度补偿[J]. 光学精密工程, 2014,22(11): 2975-2982

SHI Zhen, CHEN Shuai, ZHANG Jian etc. Temperature compensation of laser gyro based on improved RBF neural network[J]. Editorial Office of Optics and Precision Engineering, 2014,22(11): 2975-2982
史震, 陈帅, 张健等. 基于改进径向基函数神经网络的激光陀螺温度补偿[J]. 光学精密工程, 2014,22(11): 2975-2982 DOI： 10.3788/OPE.20142211.2975.

SHI Zhen, CHEN Shuai, ZHANG Jian etc. Temperature compensation of laser gyro based on improved RBF neural network[J]. Editorial Office of Optics and Precision Engineering, 2014,22(11): 2975-2982 DOI： 10.3788/OPE.20142211.2975.

摘要

传统的径向基神经网络(RBFNN)在激光陀螺零偏的温度补偿过程中会由于随机选取中心不合适而导致算法效率降低和数值病态

故本文提出了一种基于Kohonen网络和正交最小二乘(OLS)算法的RBFNN温度补偿方法。介绍了该方法的原理及建模步骤

设计了常温和变温环境下激光陀螺的数据采集试验及其温度补偿试验。由于结合了Kohonen网络的模式分类能力和OLS的优化选择能力

该方法可以快速、准确地辨识出受温度影响的激光陀螺零偏。利用逐步回归法、RBFNN法及其改进方法对多种温变环境影响的激光陀螺零偏进行了辨识与补偿试验

试验结果表明

在常温环境下

三者的辨识能力相当;随着温变速率的上升

改进RBFNN法不仅节省了时间

其补偿后的零偏也均小于510

-4

()/h(1)

提高精度均能达86%以上。得到的结果表明改进RBFNN法提高了辨识精度且稳定、有效

适用于多种温度变化环境下激光陀螺零偏的温度补偿。

Abstract

When the Radial Basis Function Neural Network (RBFNN)is used for the temperature compensation of a laser gyro bias

it shows lower computing efficiency and numerical pathology due to incorrecting selection of an initial center randomly. Therefore

this paper proposes a new RBFNN method based on the Kohonen network and Orthogonal Least Squares (OLS) algrithm. It introduces the principle and modeling steps of the method and designs data collection and temperature compensation experiments of the laser gyro under normal temperature and variable temperature environments. As the method combines the pattern classification capability of the Kohonen network and the optimal choice capacity of the OLS

it avoids the effect of drawback mentioned above

and can quickly and accurately identify the laser gyro bias affected by temperatures. The identification and compensation tests for the laser gyro bias effected by a variety of temperature change situations are performed by the stepwise regression method

RBFNN method and the proposed modified methods in this paper. The test results show that the three methods all have the abilities to identify fairly in the situation of normal temperature; with increasing the rate of temperature change

proposed RBFNN method not only saves time

the compensated laser gyro bias is all also less than 510

-4

()/h (1)

and its accuracy is improved more than 86%. The proposed RBFNN method enhances the stability and effectiveness of identification accuracy

and is suitable for laser gyro bias temperature compensation in a variety of temperature change conditions.

关键词

Keywords

references

CHENG J C, FANG J C. Comparison of compensation methods on RLG temperature error and their application in POS[C]. Proceedings of the 8th International Symposium on Instrumentation and Control Technology, London, IEEE, 2012:189-194.

李文贤. 激光陀螺捷联惯导系统温度误差建模与补偿方法研究[D]. 长沙:国防科学技术大学,2010. LI W X. Research on temperature modeling and compensating of ring laser gyroscope strapdown inertial navigation system[D]. Changsha: National University of Defense Technology,2010. (in Chinese)

葛文涛,陈明刚,林玉荣,等. 三轴激光陀螺温度误差动态建模及补偿技术[J]. 光学精密工程,2007,15(10):1509-1514. GE W T, CHEN M G, LIN Y R, et al.. Dynamic modeling and compensation for thermal error of three-axis ring laser gyro[J]. Opt. Precision Eng., 2007,15(10): 1509-1514. (in Chinese)

贾方秀,裘安萍,施芹,等. 硅微振动陀螺仪设计与性能测试[J]. 光学精密工程,2013,21(5):1272-1281. JIA F X, QIU A P, SHI Q, et al.. Design and experiment of micro machined vibratory gyroscope[J]. Opt. Precision Eng., 2013,21(5): 1272-1281. (in Chinese)

张鹏飞,龙兴武. 二频机抖激光陀螺零偏的温度特性的逐步回归分析[J]. 光学技术,2006,32(5):738-740. ZHANG P F, LONG X W. Analysis on temperature characteristic of mechanically dithered RLG's bias with a method of stepwise regression[J]. Optical Technique, 2006,32(5),738-740. (in Chinese)

金靖,张忠钢,王峥,等. 基于RBF神经网络的数字闭环光纤陀螺温度误差补偿[J]. 光学精密工程,2008,16(2):235-240. JIN J, ZHANG ZH G, WANG ZH, et al.. Temperature error compensation for digital closed-loop fiber optic gyroscope based on RBF neural network[J]. Opt. Precision Eng., 2008,16(2):235-240. (in Chinese)

韩连洋,高博,杨柳. 车载陆基导弹惯导系统温度补偿技术方法[J]. 战术导弹技术,2013,(4):81-85. HAN L Y,GAO B,YANG L. Study of temperature compensation for laser gyro SINS of land-based missile[J]. Tactical Missile Technology,2013,(4):81-85. (in Chinese)

沈军,缪玲娟,吴军伟,等. 基于RBF神经网络的光纤陀螺启动补偿及应用[J]. 红外与激光工程,2013,42(1):119-124. SHEN J, MIAO L J, WU J W, et al.. Application and compensation for startup phase of FOG based on RBF neural network[J]. Infrared and Laser Engineering, 2013,42(1): 119-124. (in Chinese)

于旭东,魏学通,李莹,等. RBF神经网络在单轴旋转惯导系统轴向陀螺漂移辨识中的应用[J]. 国防科技大学学报,2012,34(6):48-52. YU X D, WEI X T, LI Y, et al.. Application of radial Basis function network for identification of axial RLG drifts in single-axis rotation inertial navigation system[J]. Journal of National University of Defense Technology, 2012,34(6): 48-52. (in Chinese)

庞鸿锋,罗飞路,陈棣湘,等. 磁力仪温度误差的径向基神经网络补偿模型[J]. 仪器仪表学报 2012,33(3):395-700. PANG H F, LUO F L, CHEN D X, et al.. Temperature compensation model of fluxgate magnetometers based on RBF neural network[J]. Chinese Journal of Scientific Instrument, 2012,33(3): 395-700. (in Chinese)

吴艳,郑学理,曾志强,等. 倾角传感器温度特性研究[J]. 电子测量技术,2012,35(10):8-12,20. WU Y, ZHENG X L, ZENG ZH Q, et al.. Research on temperature characteristic of angle sensor[J]. Electronic Measurement Technology, 2012,35(10): 8-12,20. (in Chinese)

行鸿彦,彭基伟,吕文华,等. 一种湿度传感器温度补偿的融合算法[J]. 传感技术学报,2012,25(12):1711-1716. XING H Y, PENG J W, LV W H, et al.. A fusion algorithm for humidity sensor temperature compensation[J]. Chinese Journal of Sensors and Actuators, 2012,25(12): 1711-1716. (in Chinese)

孙艳梅,都文和,冯昌浩,等. 基于蚁群聚类算法的RBF神经网络在压力传感器中的应用[J]. 传感技术学报,2013,26(6):806-809. SUN Y M, DU W H, FENG CH H, et al.. The application of RBF neural network based on ant colony clustering algorithm to pressure sensor[J]. Chinese Journal of Sensors and Actuators, 2013,26(6): 806-809. (in Chinese)

KOHONEN T. Engineering Application of self-organizing map[J]. PIEEE, 1996,84(10): 1358-1384.

浏览量

370

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于信息融合实现的激光陀螺调腔检测