基于长短期记忆神经网络的自适应容错方法

doi:10.12305/j.issn.1001-506X.2023.03.25

摘要/Abstract

摘要：

针对传统的全球导航卫星系统/惯性导航系统(global navigation satellite system/inertial navigation system, GNSS/INS)紧组合系统容错方法对故障处理方式单一、环境适应性差的问题, 提出了一种基于长短期记忆神经网络的自适应故障容错方法。该方法基于长短期记忆神经网络建立GNSS伪距、伪距率预测模型。发生故障时, 通过分量检测法定位故障观测的维度, 并引入相对差分定位精度分析故障观测对系统定位精度的影响, 从而实现隔离与重构策略的动态选择。利用实测数据从可见星数、几何构型、故障持续时间3个角度设置多组环境进行仿真实验。仿真结果表明, 所提方法对复杂环境具有更好的适应能力, 可有效降低故障存续期间系统的定位误差, 提高系统的故障检测性能。

关键词: 全球导航卫星系统/惯性导航系统紧组合, 容错, 长短期记忆神经网络, 定位精度, 故障检测

Abstract:

Aiming at the problem that the traditional fault-tolerant method of tightly coupled global navigation satellite system/inertial navigation system (GNSS/INS) is insufficient to adapt to the environment and to solve the fault, an adaptive fault-tolerant method based on long-term and short-term memory neural network is proposed. In this method, GNSS pseudo-range and pseudo-range rate prediction models were established based on long and short-term memory neural network. When a fault occurs, the dimension of the fault observation is located by the component detection method, and the relative differential precision of positioning is introduced to analyze the impact of the fault observation on the positioning accuracy of the system and to realize the dynamic selection of the isolation and reconfiguration strategy. Utilizing the actual measurement data, simulation experiments are conducted by setting up multiple environments from three perspectives: number of visible stars, geometric configuration, and fault duration. The simulation results show that the proposed method has better adaptability to complex environments, and can effectively reduce the localization error of the system during faults existing period and improve the fault detection performance of the system.

Key words: tightly coupled global navigation satellite system/inertial navigation system(GNSS/INS), fault-tolerant, long-short term memory (LSTM) neural network, positioning accuracy, fault detection

中图分类号:

V249.3

沈子涵, 赵修斌, 张闯, 张良, 刘鑫贤. 基于长短期记忆神经网络的自适应容错方法[J]. 系统工程与电子技术, 2023, 45(3): 831-838.

Zihan SHEN, Xiubin ZHAO, Chuang ZHANG, Liang ZHANG, Xinxian LIU. Adaptive fault-tolerant method based on long-short term memory neural network[J]. Systems Engineering and Electronics, 2023, 45(3): 831-838.

图/表 11

图1

图2

表1

图3

图4

表2

表3

图5

图6

表4

图7

参考文献 33

1	罗凯鑫, 吴美平, 范颖. 基于最大熵方法的鲁棒自适应滤波及其应用[J]. 系统工程与电子技术, 2020, 42 (3): 667- 673.
	LUO K X , WU M P , FAN Y . Robust adaptive filtering based on maximum entropy method and its application[J]. Systems Engineering and Electronics, 2020, 42 (3): 667- 673.
2	PAN W C , ZHAN X Q , ZHANG X , et al. A subset-reduced method for FDE ARAIM of tightly-coupled GNSS/INS[J]. Sensors, 2019, 19 (22): 4847. doi: 10.3390/s19224847
3	张闯, 赵修斌, 庞春雷, 等. LS-SVM辅助的小幅值及缓变故障检测与容错方法[J]. 中国惯性技术学报, 2019, 27 (3): 415- 420.
	ZHANG C , ZHAO X B , PANG C L , et al. LS-SVM assisted fault detection and tolerance method for small-amplitude fault and gradual fault[J]. Journal of Chinese Inertial Technology, 2019, 27 (3): 415- 420.
4	JIANG W , LIU D , CAI B G , et al. A fault-tolerant tightly coupled GNSS/INS/OVS integration vehicle navigation system based on an FDP algorithm[J]. IEEE Trans.on Vehicular Technology, 2019, 68 (99): 6365- 6378.
5	DU S , GAN X D , ZHANG R Q , et al. The integration of rotary MEMS INS and GNSS with artificial neural networks[J]. Mathe-matical Problems in Engineering, 2021, 2021, 6669682.
6	苏敬, 何华锋, 何耀民, 等. 考虑SAR量测特性的弹载SINS/SAR组合导航滤波算法[J]. 系统工程与电子技术, 2021, 43 (4): 1044- 1049.
	SU J , HE H F , HE Y M , et al. Filtering algorithm of missile-borne SINS/SAR integrated navigation considering SAR mea-surement characteristics[J]. Systems Engineering and Electro-nics, 2021, 43 (4): 1044- 1049.
7	SHEN C , XIONG Y F , ZHAO D H , et al. Multi-rate strong tracking square-root cubature Kalman filter for MEMS-INS/GPS/polarization compass integrated navigation system[J]. Mechanical Systems and Signal Processing, 2022, 163 (1): 108146.
8	王巍, 邢朝洋, 冯文帅. 自主导航技术发展现状与趋势[J]. 航空学报, 2021, 42 (11): 525049.
	WANG W , XING C Y , FENG W S . Sate of the art and perspectives of autonomous navigation technology[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42 (11): 525049.
9	孙淑光, 温启新. 基于高程异常补偿的飞机终端区组合导航高度优化算法[J]. 系统工程与电子技术, 2021, 43 (9): 2612- 2619.
	SUN S G , WEN Q X . Aircraft height optimization algorithm of integrated navigation in terminal area based on height anomaly compensation[J]. Systems Engineering and Electronics, 2021, 43 (9): 2612- 2619.
10	陈莹超, 熊继军, 周兆英, 等. 基于短期数据融合的自主三维导航系统[J]. 仪表技术与传感器, 2017, 2017 (1): 130- 133. 130-133, 138 doi: 10.3969/j.issn.1002-1841.2017.01.033
	CHEN Y C , XIONG J J , ZHOU Z Y , et al. Independent 3D navigation system based on short-term data fusion[J]. Instrument Technology and Sensors, 2017, 2017 (1): 130- 133. 130-133, 138 doi: 10.3969/j.issn.1002-1841.2017.01.033
11	ZHANG C, ZHAO X B, PANG C L, et al. Improved fault detection and tolerance method based on local test and adaptively robust filtering for INS/GNSS integration[C]//Proc. of the IEEE Chinese Control and Decision Conference, 2019: 5919-5924.
12	董毅, 王鼎杰, 吴杰. 载波相位时间差分辅助的SINS/GNSS紧组合导航方法[J]. 中国惯性技术学报, 2021, 29 (4): 451- 458.
	DONG Y , WANG D J , WU J . MEMS-based SINS/GNSS tightly-coupled navigation aided by time-differenced carrier-phase measurements[J]. Journal of Chinese Inertial Technology, 2021, 29 (4): 451- 458.
13	NAGAI K, SPENKO M, HENDERSON R, et al. Evaluating INS/GNSS availability for self-driving cars in urban environments[C]//Proc. of the International Technical Meeting of the Institute of Navigation, 2021: 243-253.
14	YAO Y Q , XU X S , ZHU C C , et al. A hybrid fusion algorithm for GPS/INS integration during GPS outages[J]. Mea-surement, 2017, 103, 42- 51.
15	ZHANG C , ZHAO X B , PANG C L , et al. The influence of satellite configuration and fault duration time on the perfor-mance of fault detection in GNSS/INS integration[J]. Sensors, 2019, 19 (9): 2147.
16	TEUNISSEN P . Distributional theory for the DIA method[J]. Journal of Geodesy, 2018, 92 (1): 59- 80.
17	ZHANG C , ZHAO X B , PANG C L , et al. Adaptive fault isolation and system reconfiguration method for GNSS/INS integration[J]. IEEE Access, 2020, 8, 17121- 17133.
18	WANG L H , ZHI K Y , LI B , et al. Dynamically adjusting filter gain method for suppressing GNSS observation outliers in integrated navigation[J]. Journal of Navigation, 2018, 71 (6): 1396- 1412.
19	苗岳旺, 周巍, 田亮, 等. 基于新息χ²检测的扩展抗差卡尔曼滤波及其应用[J]. 武汉大学学报, 2016, 41 (2): 269- 273.
	MIAO Y W , ZHOU W , TIAN L , et al. Extended robust Kalman filter based on innovation chi-square test algorithm and its application[J]. Geomatics and Information Science of Wuhan University, 2016, 41 (2): 269- 273.
20	胡晓月, 康凯, 钱骅, 等. 基于LSTM的LEO卫星链路自适应算法[J]. 系统工程与电子技术, 2021, 43 (1): 237- 243.
	HU X Y , KANG K , QIAN H , et al. Link adaptation algorithm based on LSTM network for LEO satellite[J]. Systems Engineering and Electronics, 2021, 43 (1): 237- 243.
21	WANG B , LIU S C , WANG B , et al. Multi-step ahead short-term predictions of storm surge level using CNN and LSTM network[J]. Acta Oceanologica Sinica, 2021, 40 (11): 104- 118.
22	LI B , LIANG S Y , CHEN D Q , et al. A decision-making method for air combat maneuver based on hybrid deep learning network[J]. Chinese Journal of Electronics, 2022, 31 (1): 107- 115.
23	ZHOU H , ZHOU Y H , HU J J , et al. LSTM-based energy management for electric vehicle charging in commercial-building prosumers[J]. Journal of Modern Power Systems and Clean Energy, 2021, 9 (5): 1205- 1216.
24	CHANG Y Z , WANG Y Q , SHEN Y Y , et al. A new fuzzy strong tracking cubature Kalman filter for INS/GNSS[J]. GPS Solutions, 2021, 25 (3): 120.
25	ZHANG C , ZHAO X B , PANG C L , et al. Improved fault detection method based on robust estimation and eliding window test for INS/GNSS integration[J]. Journal of Navigation, 2020, 73 (4): 776- 796.
26	ZAMINPARDAZ S , TEUNISSEN P J G . DIA-datasnooping and identifiability[J]. Journal of Geodesy, 2019, 93 (2): 85- 101.
27	CHEN C C , ZHANG Q , KASHANI M H , et al. Forecast of rainfall distribution based on fixed sliding window long short-term memory[J]. Engineering Applications of Computational Fluid Mechanics, 2022, 16 (1): 248- 261.
28	MOUATADID S , ADAMOWSKI J F , TIWARI M K , et al. Coupling the maximum overlap discrete wavelet transform and long short-term memory networks for irrigation flow forecasting[J]. Agricultural Water Management, 2019, 219 (1): 72- 85.
29	ZHANG G H , XU P H , XU H S , et al. Prediction on the urban GNSS measurement uncertainty based on deep learning networks with long short-term memory[J]. IEEE Sensors Journal, 2021, 21 (18): 20563- 20577.
30	WANG J , JIANG W P , LI Z , et al. A new multi-scale sliding window LSTM framework (MSSW-LSTM): a case study for GNSS time-series prediction[J]. Remote Sensing, 2021, 13 (16): 3328.
31	KASELIMI M , VOULODIMOS A , DOULAMIS N , et al. A causal long short-term memory sequence to sequence model for TEC prediction using GNSS observations[J]. Remote Sensing, 2020, 12 (9): 1354.
32	王鑫, 吴际, 刘超, 等. 基于LSTM循环神经网络的故障时间序列预测[J]. 北京航空航天大学学报, 2018, 44 (4): 772- 784.
	WANG X , WU J , LIU C , et al. Exploring LSTM based recurrent neural network for failure time series prediction[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44 (4): 772- 784.
33	李世玺. 一种基于混沌理论和LSTM的GPS高程时间序列预测方法[J]. 导航定位学报, 2020, 8 (1): 65- 73.
	LI S X . A GPS height time series prediction method based on chaos theory and LSTM[J]. Journal of Navigation and Posi-tioning, 2020, 8 (1): 65- 73.

参数	陀螺仪	加速度计
零偏	20(°)/h	50 mg
零偏稳定性	±1(°)/h	±0.75 mg
刻度因子	1 500 ppm	4 000 ppm

模型	131~190 s		261~320 s
模型	MAD	RMSE	MAD	RMSE
模型1	2.211	3.140	4.016	4.884
模型2	1.406	1.704	0.480	0.582

环境	故障时间	可见星数	故障卫星号	几何构型
环境1 环境2	199~219 s	9 5	7	相同
环境3 环境4	256~276 s	6	6	构型1 构型2
环境5	69~119 s	5	1	-

环境	维度	M1	M2	M3
环境2	经度	2.407	3.202	0.216
	纬度	1.927	2.901	0.255
	高度	1.316	4.989	0.679
环境3	经度	1.413	2.713	0.537
	纬度	0.940	1.809	0.350
	高度	6.088	11.542	1.546
环境5	经度	4.082	20.169	0.814
	纬度	1.823	8.964	0.740
	高度	17.245	49.609	3.146

[1]	王晓伟, 詹亚锋, 谢浩然, 陈曦. 通导一体化环月星座设计初探[J]. 系统工程与电子技术, 2023, 45(1): 241-249.
[2]	聂倩, 杨丽花, 呼博, 任露露. 基扩展模型下基于LSTM神经网络的时变信道预测方法[J]. 系统工程与电子技术, 2022, 44(9): 2971-2977.
[3]	张普, 薛惠锋, 高山, 左轩. 具有混合执行器故障的多智能体分布式有限时间自适应协同容错控制[J]. 系统工程与电子技术, 2022, 44(4): 1220-1229.
[4]	张心宇, 刘源, 宋佳凝. 基于LSTM神经网络的短期轨道预报[J]. 系统工程与电子技术, 2022, 44(3): 939-947.
[5]	朱敏, 刘奇, 刘星, 许晴. 基于LMKL和OC-ELM的航空电子部件故障检测方法[J]. 系统工程与电子技术, 2020, 42(6): 1424-1432.
[6]	谢皓宇, 邱静, 杨鹏. 考虑单元互测的测试性指标分配方法[J]. 系统工程与电子技术, 2019, 41(12): 2899-2904.
[7]	彭雅奇, 许承东, 牛飞, 李臻, 范国超. 基于鲁棒扩展卡尔曼粒子滤波的RAIM算法[J]. 系统工程与电子技术, 2018, 40(12): 2790-2796.
[8]	许兆新, 李航洲, 李亮, 赵琳, 刘亚. 基于EKF/SF的BDS短基线多径抑制方法[J]. 系统工程与电子技术, 2017, 39(6): 1334-1340.
[9]	马龙, 代超璠, 裴昕, 黄超, 张鸿燕, 苏志刚. MEMS陀螺仪冗余配置故障检测方法[J]. 系统工程与电子技术, 2017, 39(10): 2298-2304.
[10]	赵琳, 张胜宗, 李亮, 王雪. #br# 基于自适应EKF的BDS/GPS精密单点定位方法[J]. 系统工程与电子技术, 2016, 38(9): 2142-2148.
[11]	许立波, 李兴森, 沈斌, 庞超逸. 基于广义混合图的弱节点对等覆盖网络结构[J]. 系统工程与电子技术, 2016, 38(7): 1673-1680.
[12]	吕迅竑, 姜斌, 陈欣, 齐瑞云. 无人机容错飞行控制计算机体系结构研究[J]. 系统工程与电子技术, 2016, 38(11): 2586-2597.
[13]	任文娟, 周志鑫, 吕守业, 师栋锋. 基于AIS信息的舰船位置标校方法[J]. 系统工程与电子技术, 2016, 38(10): 2381-2388.
[14]	刘兴川, 吴振锋, 赵克俭. 异构多跳无线传感器网络容错性拓扑控制算法[J]. 系统工程与电子技术, 2015, 37(8): 1902-1908.
[15]	赵玉新，常帅，万程程. 考虑故障检测效用与修正效用的软件可靠性增长模型[J]. 系统工程与电子技术, 2015, 37(4): 969-973.