融合机理与数据的陀螺飞轮姿态测量方法

doi:10.12305/j.issn.1001-506X.2025.10.29

摘要/Abstract

摘要：

针对陀螺飞轮非调谐大倾侧运行工况下姿态敏感机理复杂、测量精度低等问题，提出一种融合姿态测量机理与深度神经网络补偿的姿态测量方法。以陀螺飞轮的径向动力学模型为基础，在考虑内部传感器配置约束的前提下，基于简化假设构建机理测量模型。设计注意力机制与长短时记忆网络集成的深度学习回归模型，通过挖掘姿态测量误差与陀螺飞轮运行状态数据间的潜在关系实现测量误差补偿。提出基于机理与数据驱动的融合方法，使得陀螺飞轮以较高精度测量外部载体的角速度。通过对比实验验证了所提方法的测量精度提升效果和优越性能。

关键词: 陀螺飞轮, 姿态测量, 测量机理, 误差补偿, 深度学习

Abstract:

Gyrowheel is always operating at de-tuned spin speed and large tilt angles, which leads to its complicated mechanism and low precision for attitude measurement. To solve this problem, an attitude measurement method is proposed that combines the attitude operating mechanism with the deep neural network-based error compensation. In consideration of the sensor configuration constraints of the gyrowheel system, a mechanism-based measurement model is constructed based on the transverse-axes dynamics through the simplification of assumptions. Besides, a deep learning-based regression model is developed by integrating a long short-term memory network and a dual-channel attention mechanism. It explores the potential relationship between the measurement errors and the operating status of the gyrowheel, yielding the error compensation for the mechanism-based model. On this basis, a hybrid attitude measurement approach is presented, which offers a high-precision way to estimate the external angular velocities of the gyrowheel. The precision improvement and superior performance are verified through comparative experiments.

Key words: gyrowheel, attitude measurement, measurement mechanism, error compensation, deep learning

中图分类号:

V 448.2

赵昱宇, 刘耀蓬, 王雨潇. 融合机理与数据的陀螺飞轮姿态测量方法[J]. 系统工程与电子技术, 2025, 47(10): 3455-3463.

Yuyu ZHAO, Yaopeng LIU, Yuxiao WANG. Attitude measurement approach for gyrowheel based on integrating mechanism and data[J]. Systems Engineering and Electronics, 2025, 47(10): 3455-3463.

图/表 9

图1

图2

图3

表1

表2

图4

图5

图6

图7

参考文献 31

1	TURAN E, SPERETTA S, GILL E. Autonomous navigation for deep space small satellites: scientific and technological advances[J]. Acta Astronautica, 2022, 193, 56- 74. doi: 10.1016/j.actaastro.2021.12.030
2	HAN C, XIONG W, XIONG M H, et al. Support vector regression-based operational effectiveness evaluation approach to reconnaissance satellite system[J]. Journal of Systems Engineering and Electronics, 2023, 34 (6): 1626- 1644. doi: 10.23919/JSEE.2023.000020
3	MÜLLER L, CHEN K K, MÖLLER G, et al. Real-time navigation solutions of low-cost off-the-shelf GNSS receivers on board the astrocast constellation satellites[J]. Advances in Space Research, 2024, 73 (1): 2- 19. doi: 10.1016/j.asr.2023.10.001
4	LEE D Y, PARK H, ROMANO M, et al. Development and experimental validation of a multi-algorithmic hybrid attitude determination and control system for a small satellite[J]. Aerospace Science and Technology, 2018, 78, 494- 509. doi: 10.1016/j.ast.2018.04.040
5	MANSOURI A, ALEM-TABRIZ A. Redundancy allocation optimizing in the satellite attitude determination and control system based on the exact solution algorithm[J]. Communications in Statistics-Theory and Methods, 2024, 53 (4): 1516- 1534. doi: 10.1080/03610926.2022.2104873
6	王平, 王华, 任元. 基于磁悬浮转子微框架能力的航天器姿态二自由度测控一体化控制方法[J]. 系统工程与电子技术, 2016, 38 (7): 1614- 1622. doi: 10.3969/j.issn.1001-506X.2016.07.21
	WANG P, WANG H, REN Y. Spacecraft attitude integration method of measurement and control in two degrees of freedom based on micro framework ability of magnetically suspended rotor[J]. Systems Engineering and Electronics, 2016, 38 (7): 1614- 1622. doi: 10.3969/j.issn.1001-506X.2016.07.21
7	CHEN S, HUO X, ZHAO H, et al. Active tilting flutter suppression of gyrowheel with composite-structured adaptive compensator[J]. IEEE Trans. on Industrial Electronics, 2021, 68 (7): 6227- 6237. doi: 10.1109/TIE.2020.2994858
8	FANG J C, ZHENG S Q, HAN B C. Attitude sensing and dynamic decoupling based on active magnetic bearing of MSDGCMG[J]. IEEE Trans. on Instrumentation and Measurement, 2012, 61 (2): 338- 348. doi: 10.1109/TIM.2011.2164289
9	STALEY D A, TYC G, FRIESE P R. System and method for spacecraft attitude control[P]. US: US20020040950A1, 2002-04-11.
10	HALL J M. Calibration of an innovative rate sensing/momentum management instrument for de-tuned operation and temperature effects[D]. Ottawa: Carleton University, 2008.
11	GUO J, ZHONG M Y. Calibration and compensation of the scale factor errors in DTG POS[J]. IEEE Trans. on Instrumentation and Measurement, 2013, 62 (10): 2784- 2794. doi: 10.1109/TIM.2013.2261631
12	赵砚驰, 程建华, 赵琳. 惯性导航系统陀螺仪的发展现状与未来展望[J]. 导航与控制, 2020, 19 (Z1): 189- 196.
	ZHAO Y C, CHENG J H, ZHAO L. Development status and future prospects of gyroscope in inertial navigation[J]. Navigation and Control, 2020, 19 (Z1): 189- 196.
13	YU C M, CAI Y W, REN Y, et al. A full-frequency angular rate measurement method of spacecraft based on multi-MSCSG weight assignment[J]. IEEE Sensors Journal, 2023, 23 (8): 8304- 8313. doi: 10.1109/JSEN.2023.3258442
14	张晗, 张宇, 赵辉. 陀螺飞轮动力学特征分析[J]. 系统仿真学报, 2015, 27 (1): 112- 117.
	ZHANG H, ZHANG Y, ZHAO H. Dynamics analysis of gyrowheel for its micro-spacecraft attitude control application[J]. Journal of System Simulation, 2015, 27 (1): 112- 117.
15	OWER J C. Analysis and control system design of an innovative tuned-rotor instrument[D]. Ottawa: Carleton University, 2000.
16	LIU X K, ZHAO H, YAO Y, et al. Modeling and analysis of micro-spacecraft attitude sensing with gyrowheel[J]. Sensors, 2016, 16 (8): 1321. doi: 10.3390/s16081321
17	LIU X K, YAO Y, MA K M, et al. Spacecraft angular rates estimation with gyrowheel based on extended high gain observer[J]. Sensors, 2016, 16 (4): 537. doi: 10.3390/s16040537
18	ZHAO Y Y, ZHAO H, HUO X, et al. A novel external rate sensing algorithm for gyrowheel based on Jacobi-Anger expansion[J]. IEEE Sensors Journal, 2019, 19 (16): 6662- 6674. doi: 10.1109/JSEN.2019.2912390
19	CHEN S, HUO X, ZHAO H, et al. Axial unbalance identification of gyrowheel rotor based on multi-position calibration and CEEMDAN-IIT denoising[J]. Measurement, 2021, 183, 109852. doi: 10.1016/j.measurement.2021.109852
20	ZHAO Y Y, ZHAO H, HUO X, et al. A novel two-step parameter identification method for gyrowheel system[J]. Measurement, 2019, 136, 367- 381. doi: 10.1016/j.measurement.2018.12.082
21	KIKUYA Y, OHTA K, IWASAKI Y, et al. Development and in-orbit operation of deep learning attitude sensor[J]. Journal of Spacecraft and Rockets, 2023, 60 (5): 1400- 1409. doi: 10.2514/1.A35388
22	SOUFI O, BELOUADHA F Z. An intelligent deep learning approach to spacecraft attitude control: the case of satellites[J]. Journal of the Franklin Institute-Engineering and Applied Mathematics, 2024, 361 (14): 107078. doi: 10.1016/j.jfranklin.2024.107078
23	MOHAMED M I, BADRAN K M, HUSSIEN A E. Anomaly detection for agile satellite attitude control system using hybrid deep-learning technique[J]. Journal of Aerospace Information Systems, 2023, 20 (12): 890- 904.
24	程向红, 吴昕怡, 刘丰宇, 等. 基于改进LSTM网络的无人机MEMS-IMU零偏在线标定方法[J]. 中国惯性技术学报, 2024, 32 (3): 213- 218.
	CHENG X H, WU X Y, LIU F Y, et al. An improved LSTM neural network online calibration method of MEMS-IMU bias for UAV[J]. Journal of Chinese Inertial Technology, 2024, 32 (3): 213- 218.
25	CHEN Y D, JIANG W, WANG J, et al. An LSTM-assisted GNSS/INS integration system using IMU recomputed error information for train localization[J]. IEEE Trans. on Aerospace and Electronic Systems, 2024, 60 (3): 2658- 2671. doi: 10.1109/TAES.2023.3328318
26	GOLROUDBARI A A, SABOUR M H. Generalizable end-to-end deep learning frameworks for real-time attitude estimation 6DoF inertial measurement units[J]. Measurement, 2023, 217, 113105. doi: 10.1016/j.measurement.2023.113105
27	LIN C Y, ZHEN R, TONG Y T, et al. Regional ship collision risk prediction: an approach based on encoder-decoder LSTM neural network model[J]. Ocean Engineering, 2024, 296, 117019. doi: 10.1016/j.oceaneng.2024.117019
28	LE-DUC T, NGUYEN-XUAN H, LEE J. Sequential motion optimization with short-term adaptive moment estimation for deep learning problems[J]. Engineering Applications of Artificial Intelligence, 2024, 129, 107593. doi: 10.1016/j.engappai.2023.107593
29	ZHENG Y, CHEN C X, WANG R Q, et al. Stability analysis of rock slopes subjected to block-flexure toppling failure using adaptive moment estimation method （Adam）[J]. Rock Mechanics and Rock Engineering, 2022, 55 (6): 3675- 3686. doi: 10.1007/s00603-022-02828-5
30	刘晓坤. 基于陀螺飞轮的航天器姿态角速度测量方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2018.
	LIU X K. Study on spacecraft attitude angular velocity measurement method based on gyrowheel[D]. Harbin: Harbin Institute of Technology, 2018.
31	ZHAO Q, YAO Y, LIU X K, et al. Modeling and analysis of gyrowheel with friction and dynamic unbalance[C]// Proc. of the Asian Simulation Conference, 2016: 262−271.

参数	设计值	真实值
I_rt/（kg·m²）	1.11×10⁻³	1.01×10⁻³
I_rs/（kg·m²）	1.96×10⁻³	1.94×10⁻³
I_gt/（kg·m²）	1.61×10⁻⁵	1.62×10⁻⁵
I_gs/（kg·m²）	2.39×10⁻⁵	2.40×10⁻⁵
k_g/（N·m/rad）	5.60×10⁻¹	5.50×10⁻¹
c_g/（ N·m/（rad/s））	6.54×10⁻⁴	6.65×10⁻⁴

参数	设置值
传感器维数	5
时间窗长度	8
编码器隐层单元数	30
解码器隐层单元数	30
回归模块隐层节点数	50
输出维数	1

[1]	李开明, 张袁鹏, 罗迎, 代肖楠. 弹道导弹雷达目标识别研究进展[J]. 系统工程与电子技术, 2025, 47(9): 2870-2889.
[2]	季策, 马相宇, 牟晓宇, 赵家毅. TS-GRU-VTA：基于深度学习的车辆信道估计方案[J]. 系统工程与电子技术, 2025, 47(9): 3093-3098.
[3]	闫小伟, 凌冲, 石胜斌. 地表未爆子弹药快速检测系统设计与实现[J]. 系统工程与电子技术, 2025, 47(8): 2639-2645.
[4]	张琬滢, 高由兵, 李泽一, 李鹏飞, 张伟. 基于双路径特征融合网络的背景信号抑制算法[J]. 系统工程与电子技术, 2025, 47(7): 2406-2413.
[5]	张新征, 闫梦可, 朱晓林. 噪声伪标签容忍的半监督SAR目标识别[J]. 系统工程与电子技术, 2025, 47(6): 1796-1805.
[6]	姜智杰, 宋恒, 胡楠, 段兰茜, 曹平. 隧道环境毫米波雷达目标识别与分类算法[J]. 系统工程与电子技术, 2025, 47(5): 1453-1460.
[7]	聂千祁, 沙明辉, 朱应申, 王崇宇, 崔念强. 基于盲源分离结合奇异谱分析的雷达多分量信号识别方法[J]. 系统工程与电子技术, 2025, 47(4): 1168-1175.
[8]	袁磊, 杨艳娟, 郭毅, 戴鹏. 相关噪声下基于深度学习的LDPC码码率半盲识别算法[J]. 系统工程与电子技术, 2025, 47(4): 1335-1345.
[9]	沈夏闰, 李若楠, 张昊田. 基于CVAE-LSTM的服务器KPI异常检测[J]. 系统工程与电子技术, 2025, 47(3): 1019-1027.
[10]	刘晓琳, 郭梦娇, 李卓. Dueling DQN优化下的航班延误自适应图卷积循环网络预测方法[J]. 系统工程与电子技术, 2025, 47(2): 568-579.
[11]	付卫红, 张鑫钰, 刘乃安. 基于多尺度融合神经网络的同频同调制单通道盲源分离算法[J]. 系统工程与电子技术, 2025, 47(2): 641-649.
[12]	高飞, 席睿达, 邢相薇, 邢妍, 张强, 党红杏. SAR有源干扰分类识别图像数据集仿真构建[J]. 系统工程与电子技术, 2025, 47(10): 3257-3269.
[13]	朱世杰, 陈广东, 刘秉奇. 参照波结构的飞行器对接姿态快速估计[J]. 系统工程与电子技术, 2024, 46(9): 2926-2934.
[14]	蔡伟, 王鑫, 蒋昕昊, 杨志勇, 陈栋. 基于解耦的小样本目标检测方法研究[J]. 系统工程与电子技术, 2024, 46(9): 2941-2950.
[15]	陈晓萱, 徐书文, 胡绍海, 马晓乐. 基于卷积与自注意力的红外与可见光图像融合[J]. 系统工程与电子技术, 2024, 46(8): 2641-2649.