双层双向长短期记忆应用于云轨精确定位

姚顺宇; 颜国正

doi:10.3788/OPE.20202801.0166

您当前的位置：

首页 >

文章列表页 >

双层双向长短期记忆应用于云轨精确定位

信息科学 | 更新时间：2020-08-13

- 双层双向长短期记忆应用于云轨精确定位
- Precise positioning of cloud track by bi-direction long short memory
- 光学精密工程 2020年28卷第1期页码：166-173
- 作者机构：
  
  College of Instrumental Engineering, Shanghai Jiao Tong University Shanghai 200240, China
- 作者简介：
  
  [ "姚顺宇(1994-)，男，陕西延安人，硕士，2016年于西安交通大学获得学士学位, 主要从事数据融合，机器学习方面的研究。E-mail:ysy2017@sjtu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金资助项目(61673271);国家自然科学基金资助项目(81601631);国家重点研发计划资助项目(2018YFC0807405)
- DOI：10.3788/OPE.20202801.0166
  中图分类号： TP394.1; TH691.9
- 收稿日期：2019-06-17，
  
  录用日期：2019-9-29，
  
  纸质出版日期：2020-01-15
- 稿件说明：
移动端阅览
姚顺宇, 颜国正. 双层双向长短期记忆应用于云轨精确定位[J]. 光学精密工程, 2020,28(1):166-173.

Shun-yu YAO, Guo-zheng YAN. Precise positioning of cloud track by bi-direction long short memory[J]. Optics and precision engineering, 2020, 28(1): 166-173.
姚顺宇, 颜国正. 双层双向长短期记忆应用于云轨精确定位[J]. 光学精密工程, 2020,28(1):166-173. DOI： 10.3788/OPE.20202801.0166.

Shun-yu YAO, Guo-zheng YAN. Precise positioning of cloud track by bi-direction long short memory[J]. Optics and precision engineering, 2020, 28(1): 166-173. DOI： 10.3788/OPE.20202801.0166.

摘要

目前国内出现了一种新型云轨，云轨有着造价低、能耗小以及施工周期较短等优点。然而云轨的各项指标要求很高，其中轨道定位尤为重要。为了实现了云轨检测的精确定位，本文设计了一种新型轨道检测车，并开发了基于双层双向长短期记忆模型(LSTM)的云轨SIN-GPS定位算法。首先，介绍了轨道检测车的机械结构和各项传感器参数。接着，分析了传统的SIN-GPS定位算法及其缺点，在GPS信号消失后会出现误差积累。然后，引出双层双向长短期记忆模型，说明了该模型对GPS信号消失时的误差动态学习和补偿。最后，通过3组实验分析算法在云轨检测车的不同运动状态下的准确率。证明了长短期记忆模型均优于传统算法模型和其他智能算法模型。实验结果表明：在运动状态下LSTM算法比SINS误差小79.8%，静止状态下SINS误差最小。设定速度阈值为0.2 m/s，大于此阈值采用LSTM算法，小于此阈值直接用SINS的数据，可以得到最准确的位置预测结果。

Abstract

At present

a new type of cloud track has emerged in China. Cloud track has the advantages of low cost

low energy consumption and short construction period. This new type of cloud track requires precise positioning of track detection. In order to eliminate the position error of cloud track detection

a new type of track detection vehicle was designed

and a new SIN-GPS positioning algorithm based on double-layer bidirectional LSTM network was developed. Firstly

the construction and sensor parameters of the track detection vehicle was inod uced. Then

the traditional SIN-GPS positioning algorithm and its shortcomings was analyzed. If GPS signal disappeared

the positioning error was very large. a bi-directional LSTM algorithm was proposed to illustrate the dynamic learning and compensation of errors when GPS signals disappeared. Finally

the accuracy of the algorithm in different motion states of the cloud track detection vehicle with three groups of experiments was analyzed. The results of experiments show that LSTM algorithm is superior to traditional algorithms and other intelligent algorithms. It reveals that the error of LSTM is 79.8% smaller than that of SINS when the vehicle is moving. The error of SINS is smallest when the vehicle is static. When setting the speed threshold of 0.2 m/s

using LSTM algorithm when it is larger than this threshold

and directly using SINS when it is smaller

the most accurate location results can be obtained.

关键词

Keywords

references

张荣辉, 贾宏光, 陈涛, 等.基于四元数法的捷联式惯性导航系统的姿态解算[J].光学精密工程, 2008, 16(10):1963-1970.

ZHANG R H, JIA H G, CHEN T, et al .. Attitude solution for strapdown inertial navigation system based on quaternion algorithm[J]. Opt. Precision Eng ., 2008, 16(10): 1963-1970. (in Chinese)

CHEN X Y, SHEN C, ZHANG W B, et al .. Novel hybrid of strong tracking Kalman filter and wavelet neural network for GPS/INS during GPS outages[J]. Measurement, 2013, 46(10) : 3847-3854.

WAGSTAFF B, KELLY J. LSTM-based zero-velocity detection for robust inertial navigation[C]. 2018 International Conference on Indoor Positioning and Indoor Navigation. IEEE , 2018: 1-8.

崔留争, 高思远, 贾宏光, 等.神经网络辅助卡尔曼滤波在组合导航中的应[J].光学精密工程, 2014, 22(5):1304-1311.

CUI L ZH, GAO S Y, JIA H G, et al .. Application of neural network aided Kalman filtering to SINS/GPS[J]. Opt. Precision Eng ., 2014, 22(5): 1304-1311. (in Chinese)

李宇寰, 杨功流, 于沛, 等.基于Bagging模型的惯导系统误差抑制方法[J].中国惯性技术学报, 2017, 25(1): 63-66.

LI Y H, YANG G L, YU P, et al .. Error restraining method for SINS based on Bagging model[J]. Journal of Chinese Inertial Technology, 2017, 25(1): 63-66. (in Chinese)

CHEN C, LU X, MARKHAM A, et al .. IONet: Learning to cure the curse of drift in inertial odometry[C]. Thirty-Second AAAI Conference on Artificial Intelligence , 2018.

BHATT D, AGGARWAL P, DEVABHAKTUNI V, et al .. A new source difference artificial neural network for enhanced positioning accuracy[J]. Measure. Science and Technology , 2012, 23(10) :105101.

展凤江, 沈宏海, 汪沛, 等.导航信息滞后补偿实现高速无人机对地精确定位[J].光学精密工程, 2015, 23(9):2506-2512.

ZHAN F J, SHEN H H, WANG P, et al .. Precise ground target location of subsonic UAV by compensating delay of navigation information[J]. Opt. Precision Eng ., 2015, 23(9): 2506-2512. (in Chinese)

LI J, SONG N F, YANG G L, et al .. Improving positioning accuracy of vehicular navigation system during GPS outages utilizing ensemble learning algorithm[J]. Information Fusion , 2017, 35: 1-10.

储海荣, 段镇, 贾宏光, 等.捷联惯导系统的误差模型与仿真[J].光学精密工程, 2009, 17(11): 2779-2785.

CHU H R, DUAN ZH, JIA H G, et al .. Error model and simulation of strapdown inertial navigation system[J]. Opt. Precision Eng ., 2009, 17(11): 2779-2785. (in Chinese)

EL-SHAFIE A, NAJAH A, KARIM O A. Amplified wavelet-ANFIS-based model for GPS/INS integration to enhance vehicular navigation system[J]. Neural Computing and Applications , 2014, 24(7/8): 1905-1916.

ZHANG Y, SHEN C, TANG J, et al .. Hybrid algorithm based on MDF-CKF and RF for GPS/INS system during GPS outages (April 2018)[J]. IEEE Access, 2018, 6: 35343-35354.

XU J X, TAN Y. Nonlinear adaptive wavelet control using constructive wavelet networks[J]. IEEE Transactions on Neural Networks, 2007, 18(1): 115-127.

胡方强, 吕涛, 包亚萍.改进的自适应Kalman滤波在SINS/GPS组合导航中的应用[J].计算机工程与应用, 2018, 54(5):253-257.

HU F Q, LV T, BAO Y P. Application of modified adaptive Kalman filter to SINS/GPS integrated navigation system[J]. Computer Engineering and Applications , 2018, 54(5):253-257. (in Chinese)

王林, 吴文启, 魏国, 等.联合旋转调制激光陀螺惯导性能在线评估[J].光学精密工程, 2018, 26(3):578-587.

WANG L, WU W Q, WEI G, et al .. Online performance evaluation of RLG INS based on joint rotation and modulation[J]. Opt. Precision Eng ., 2018, 26(3): 578-587. (in Chinese)

TITTERTON D, WESTON J L. Strapdown Inertial Navigation Technology [M]. The Institution of Engineering and Technology, Michael Faraday House, Six Hills Way, Stevenage SG1 2AY, UK: IET, 2004.

浏览量

128

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于神经网络的全斯托克斯光电探测器

基于圆卷积神经网络的粘连导电粒子检测

面向领域自适应的部分最优传输高光谱图像分类

基于热传导和卷积神经网络的磨床主轴热误差预测

基于刚度预测-神经网络的调姿平台误差补偿