基于Elman神经网络的GNSS/INS全域高精度定位方法

doi:10.11772/j.issn.1001-9081.2018091920

计算机应用 ›› 2019, Vol. 39 ›› Issue (4): 994-1000.DOI: 10.11772/j.issn.1001-9081.2018091920

基于Elman神经网络的GNSS/INS全域高精度定位方法

邓天民^1,2, 方芳¹, 岳云霞¹, 杨其芝¹

1. 重庆交通大学交通运输学院, 重庆 400074;
2. 山区复杂道路环境"人-车-路"协同与安全重庆市重点实验室(重庆交通大学), 重庆 400074

收稿日期:2018-09-14 修回日期:2018-10-18 出版日期:2019-04-10 发布日期:2019-04-10
通讯作者: 邓天民
作者简介:邓天民(1979-),男,四川阆中人,副教授,博士,主要研究方向:交通大数据、自动驾驶、交通控制;方芳(1994-),女,四川自贡人,硕士研究生,主要研究方向:人工智能、交通信息与控制;岳云霞(1995-),女,内蒙古巴彦淖尔人,硕士研究生,主要研究方向:交通大数据;杨其芝(1994-),女,山东滕州人,硕士研究生,主要研究方向:交通大数据。
基金资助:
国家自然科学基金资助项目（51678099）；重庆市科学技术委员会科技人才培养计划项目（CSTC2013KJRC-QNRC0148）。

GNSS/INS global high-precision positioning method based on Elman neural network

DENG Tianmin^1,2, FANG Fang¹, YUE Yunxia¹, YANG Qizhi¹

1. College of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, China;
2. Chongqing Key Laboratory of"Human-Vehicle-Road"Cooperation & Safety for Mountain Complex Environment(Chongqing Jiaotong University), Chongqing 400074, China

Received:2018-09-14 Revised:2018-10-18 Online:2019-04-10 Published:2019-04-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (51678099), the Science and Technology Talents Training Program of Chongqing Science & Technology Commission (CSTC2013 KJRC-QNRC0148).

摘要/Abstract

摘要： 针对当前智能网联汽车定位与导航系统无法接收全球导航卫星系统（GNSS）信号引起定位失效的问题，提出一种基于Elman神经网络的GNSS结合惯性导航系统（INS）的全域高精度定位方法。首先，采用神经网络方法，建立了基于Elman网络的GNSS/INS高精度定位训练模型和GNSS失效预测模型；然后，利用GNSS、INS和实时动态（RTK）等定位技术，设计了GNSS/INS高精度定位数据采集实验系统；最后，选取采集的有效实验数据进行了反向传播（BP）神经网络、级联BP（CFBP）神经网络、Elman神经网络的训练模型性能对比分析，并验证了基于Elman网络的GNSS失效预测模型。实验结果表明，所提方法训练误差指标均优于基于BP和CFBP神经网络的方法；在GNSS失效1 min、2 min、5 min时，基于预测模型的预测平均绝对误差（MAE）、方差（VAR）和均方根误差（RMSE）分别为18.88 cm、19.29 cm、58.83 cm，8.96、8.45、5.68和20.90、21.06、59.10，随着GNSS信号失效时长的增加，定位预测精度降低。

关键词: 智能网联汽车, 全域高精度定位, 全球导航卫星系统, 信号失效, Elman神经网络, 数据驱动

Abstract: Aiming at positioning failure occured when positioning and navigation system of the intelligent connected vehicle fail to receive the signal of Global Navigation Satellite System (GNSS), a GNSS/Inertial Navigation System (INS) global high-precision positioning method based on Elman neural network was proposed. Firstly, a GNSS/INS high-precision positioning training model and a GNSS failure prediction model based on Elman neural network were established. Then, by using GNSS, INS and Real-Time Kinematic (RTK) and other positioning techniques, a data acquisition experiment system of GNSS/INS high-precision positioning was designed. Finally, the effective experimental data were collected to compare the performance of the training model of Back Propagation (BP) neural network, Cased-Forward BP (CFBP) neural network, Elman neural network, and the prediction model of GNSS signal outage based on Elman network was verified. The experimental results show that the training error of GNSS/INS prediction model based on Elman network is better than those based on BP and CFBP neural networks. When GNSS fails for 1 min, 2 min and 5 min, the prediction Mean Absolute Error (MAE), Variance (VAR) and Root Mean Square Error (RMSE) were 18.88 cm, 19.29 cm, 58.83 cm and 8.96, 8.45, 5.68 and 20.90, 21.06, 59.10 respectively, and with the increase of GNSS signal outage time, the positioning prediction accuracy is reduced.

Key words: intelligent connected vehicle, global high-precision positioning, Global Navigation Satellite System (GNSS), signal outage, Elman neural network, data-driven

中图分类号:

邓天民, 方芳, 岳云霞, 杨其芝. 基于Elman神经网络的GNSS/INS全域高精度定位方法[J]. 计算机应用, 2019, 39(4): 994-1000.

DENG Tianmin, FANG Fang, YUE Yunxia, YANG Qizhi. GNSS/INS global high-precision positioning method based on Elman neural network[J]. Journal of Computer Applications, 2019, 39(4): 994-1000.

参考文献

[1] SASANI S, ASGARI J, AMIRI-SIMKOOEIA A R. Improving MEMS-IMU/GPS integrated systems for land vehicle navigation application[J]. GPS Solution, 2016, 20(1):89-100.
[2] 史骏.基于组合导航系统的智能汽车精准定位[J]. 计算机与数字工程, 2018, 46(8):1487-1490, 1547. (SHI J. Precise positioning of intelligent vehicle based on integrated navigation system[J]. Computer & Digital Engineering, 2018, 46(8):1487-1490, 1547.)
[3] HAN H Z, WANG J, DU M YM. GPS/BDS/INS tightly coupled integration accuracy improvement using an improved adaptive interacting multiple model with classified measurement update[J]. Chinese Journal of Aeronautics, 2018, 31(3):556-566.
[4] LIU Y H, FAN X Q, LV C, et al. An innovative information fusion method with adaptive Kalman filter for integrated INS/GPS navigation of autonomous vehicles[J]. Mechanical Systems and Signal Processing, 2018, 100:605-616.
[5] 徐晓苏, 闫琳宇, 吴晓飞, 等.基于粒子群优化的UKF在SINS/GPS组合导航中的应用[J]. 中国惯性技术学报, 2018, 26(2):196-201. (XU X S, YAN L Y, WU X F, et al. Unscented Kalman filter based on particle swarm optimization algorithm in SINS/GPS integrated navigation system[J]. Journal of Chinese Inertial Technology, 2018, 26(2):196-201.)
[6] 张希, 缪玲娟, 郭岩冰, 等.一种新型的GPS弱信号精捕获方法[J]. 中国惯性技术学报, 2016, 24(6):752-757. (ZHANG X, MIU L J, GUO Y B, et al. Novel fine acquisition method for weak GPS signal[J]. Journal of Chinese Inertial Technology, 2016, 24(6):752-757.)
[7] 姜博文, 王可东.低成本车载组合导航在GPS失效时的算法设计[J]. 传感技术学报, 2017, 30(3):412-417. (JIANG B W, WANG K D. Algorithm design of low-cost vehicle integrated navigation system in GPS outage[J]. Chinese Journal of Sensors and Actuators, 2017, 30(3):412-417.)
[8] 张新民, 张维.GPS失锁情况下基于神经网络的组合导航算法研究[J]. 弹箭与制导学报, 2017, 37(3):13-16. (ZHANG X M, ZHANG W. Algorithm research of GPS/INS integrated system based on neural network during GPS outage[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2017, 37(3):13-16.)
[9] 王立冬, 车琳, 鲁军, 等.基于改进型灰色预测模型的SINS/GPS组合导航系统[J]. 中国惯性技术学报, 2015, 23(2):248-251, 257. (WANG L D, CHE L, LU J, et al. SINS/GPS integrated navigation system based on improved Grey forecasting model[J]. Journal of Chinese Inertial Technology, 2015, 23(2):248-251, 257.)
[10] 张威奕, 曾庆喜, 张鹏娜, 等.基于UKF的车辆GPS/蜂窝网无缝定位算法[J]. 中国惯性技术学报, 2015, 23(1):76-80. (ZHANG W Y, ZENG Q X, ZHANG P N, et al. Vehicle GPS/cellular network seamless positioning algorithm based on UKF[J]. Journal of Chinese Inertial Technology, 2015, 23(1):76-80.)
[11] 郭慧娟, 刘慧英, 石静, 等.基于自适应分类容错滤波的SINS/GNSS组合导航方法[J]. 中国惯性技术学报, 2018, 26(1):39-44. (GUO H J, LIU H Y, SHI J, et al. SINS/GNSS integrated navigation method based on adaptive classification and fault-tolerant filtering[J]. Journal of Chinese Inertial Technology, 2018, 26(1):39-44.)
[12] WYSOCKI A, LAWRYNCZUK M. Elman neural network for modeling and predictive control of delayed dynamic systems[J]. Archives of Control Sciences, 2016, 26(1):117-142.
[13] WANG Y M, ZHANG F J, CUI T. Fault diagnosis and fault-tolerant control for Manifold Absolute Pressure Sensor (MAP) of diesel engine based on elman network observer[J]. Control Engineering and Applied Informatics, 2017, 19(2):90-100.
[14] MALLESWARAN M, VAIDEHI V, SIVASANKARI N. A novel approach to the integration of GPS and INS using recurrent neural networks with evolutionary optimization techniques[J]. Aerospace Science and Technology, 2014, 32(1):169-179.
[15] YU C J, LI Y L, XIANG H Y, et al. Data mining-assisted short-term wind speed forecasting by wavelet packet decomposition and Elman neural network[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2018, 175:136-143.
[16] LIU H, MI X W, LI Y F. Wind speed forecasting method based on deep learning strategy using empirical wavelet transform, long short-term memory neural network and Elman neural network[J]. Energy Conversion and Management, 2017, 156:498-514.
[17] JON R, WANG Z S, LUO C M, et al. Adaptive robust speed control based on recurrent elman neural network for sensorless PMSM servo drives[J]. Neurocomputing, 2016, 227:131-141.
[18] DOU C X, QI H, LUO W, et al. Elman neural network based short-term photovoltaic power forecasting using association rules and kernel principal component analysis[J]. Journal of Renewable and Sustainable Energy, 2018, 10(4):043501.
[19] WEI L, WU Y Q, FU H, et al. Modeling and simulation of gas emission based on recursive modified Elman neural network[J]. Mathematical Problems in Engineering, 2018, 2018:9013839.
[20] LI X M, ZHAO T Y, ZHANG J L, et al. Predication control for indoor temperature time-delay using Elman neural network in variable air volume system[J]. Energy and Buildings, 2017, 154:545-552.
[21] ELMAN J L. Finding structure in time[J]. Cognitive Science, 1990, 14(2):179-211.
[22] KOLANOWSKI K, SWIETLICKAS A, KAPELA, R, et al. Multisensor data fusion using Elman neural networks[J]. Applied Mathematics and Computation, 2018, 319:236-244.

基于Elman神经网络的GNSS/INS全域高精度定位方法

GNSS/INS global high-precision positioning method based on Elman neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李洋莹, 陈智军, 张子豪, 游兰. 基于改进Elman神经网络的制糖企业原糖需求预测模型[J]. 计算机应用, 2021, 41(7): 2113-2120.
[2]	张效伟, 江大伟, 陈珂, 陈刚. 关系数据库中聚合代数约束的高效发现算法——AAC-Hunter[J]. 计算机应用, 2021, 41(3): 636-642.
[3]	朱昶胜, 康亮河, 冯文芳. 基于自适应鲸鱼优化算法结合Elman神经网络的股市收盘价预测算法[J]. 计算机应用, 2020, 40(5): 1501-1509.
[4]	朱霖, 宁芊, 雷印杰, 陈炳才. 基于遗传算法选优的集成手段与时序卷积网络的涡扇发动机剩余寿命预测[J]. 计算机应用, 2020, 40(12): 3534-3540.
[5]	袁志鑫, 周艳玲. 基于组合相关函数的AltBOC（15，10）信号的无模糊跟踪方法[J]. 计算机应用, 2020, 40(10): 3000-3005.
[6]	王硕, 王培良. 基于深层长短期记忆网络与批规范化的间歇过程故障检测方法[J]. 计算机应用, 2019, 39(2): 370-375.
[7]	陈辉, 蒋圭峰, 姜桂圆, 武继刚. 基于海量公交轨迹数据挖掘的地图匹配算法[J]. 计算机应用, 2018, 38(7): 1923-1928.
[8]	汪利伟, 王小艺, 王立, 白玉廷, 卢雨田. 基于双向误差传播多层神经网络的监测盲区工业废气分布分析方法[J]. 计算机应用, 2018, 38(5): 1500-1504.
[9]	殷学梅, 周军华, 朱耀琴. 复杂产品协同设计中数据建模与驱动方法[J]. 计算机应用, 2018, 38(10): 3017-3024.
[10]	刘丁浩, 吕晶, 索龙龙, 胡相誉. 载波跟踪环路统计特性分析的欺骗检测方法[J]. 计算机应用, 2017, 37(9): 2507-2511.
[11]	程进, 王坚. 基于多任务学习的炼钢终点预测方法[J]. 计算机应用, 2017, 37(3): 889-895.
[12]	曹卫东, 朱远知, 翟盼盼, 王静. 基于灰色Elman神经网络软件可靠性预测模型[J]. 计算机应用, 2016, 36(12): 3481-3485.
[13]	雷斌陶海龙徐晓光. 基于改进粒子群优化算法的灰色神经网络的铁路货运量预测[J]. 计算机应用, 2012, 32(10): 2948-2951.
[14]	吴燕红关维国王艳峰. 基于Elman神经网络的TDOA定位算法[J]. 计算机应用, 2011, 31(03): 629-631.
[15]	党小超郝占军. 基于改进Elman神经网络的网络流量预测[J]. 计算机应用, 2010, 30(10): 2648-2652.