基于神经网络的卫星姿控系统故障预测

doi:10.16182/j.issn1004731x.joss.19-FZ0351E

系统仿真学报 ›› 2019, Vol. 31 ›› Issue (11): 2499-2508.doi: 10.16182/j.issn1004731x.joss.19-FZ0351E

基于神经网络的卫星姿控系统故障预测

孟小凡¹, 宋华^1,2

1. 北京航空航天大学自动化科学与电气工程学院,北京 100191;
2. 空间智能控制技术实验室,北京 100190

收稿日期:2019-05-30 修回日期:2019-07-19 出版日期:2019-11-10 发布日期:2019-12-13
作者简介:Meng Xiaofan(1995-), Female, Hebei, Master, Research direction is satellite attitude control system fault prediction based on deep learning neural network.

Fault Prediction of Satellite Attitude Control System Based on Neural Network

Meng Xiaofan¹, Song Hua^1,2

1. School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China;
2. Science and Technology on Space Intelligent Control Laboratory, Beijing 100190, China

Received:2019-05-30 Revised:2019-07-19 Online:2019-11-10 Published:2019-12-13
Supported by:
Science and Technology on Space Intelligent Control Laboratory (HTKJ2019KL502010)

摘要/Abstract

摘要： 针对卫星姿控系统时间序列故障预测问题,给出了BP神经网络和小波神经网络、小波分解-LSTM网络相结合的故障预测方法。利用卫星正常运行时的数据训练BP神经网络,将其作为系统的标准模型,对卫星实时输出和标准模型输出之间的残差建立小波神经网络和小波分解-LSTM故障预测模型,并进行仿真对比分析。结果表明,2种方法均能准确的对故障进行预测,由于基于小波分解-LSTM的方法对残差序列进行了多级小波分解,还利用了LSTM网络能选择性保留输入数据的特点,因此预测更准确,性能更优。

关键词: 故障预测, 卫星姿态控制系统, BP神经网络, 小波神经网络, 小波分解-LSTM网络

Abstract: A new method based on BP neural network(BPNN), wavelet neural network(WNN) and wavelet decomposition-LSTM(wLSTM) network is proposed for predicting faults in the satellite attitude control system. Normal satellite attitude data is used to train BPNN which is used as the standard model of satellite attitude control system. The real-time attitude residuals is obtained by subtracting the BPNN output attitude angle from the real-time data of satellite attitude. The time series of the residuals are used to build WNN and wLSTM models to predict the faults of satellite attitude control system. A conclusion is given according to comparing the WNN and wLSTM that both the fault prediction methods can precisely predict the fault and the wLSTM model predicts more accurately because LSTM network can selectively retain the characteristics of input data. At the same time, it also provides a novel method for the prediction of complex system.

Key words: fault prediction, satellite attitude control system, BPNN, WNN, wLSTM

中图分类号:

V249.32

孟小凡, 宋华. 基于神经网络的卫星姿控系统故障预测[J]. 系统仿真学报, 2019, 31(11): 2499-2508.

Meng Xiaofan, Song Hua. Fault Prediction of Satellite Attitude Control System Based on Neural Network[J]. Journal of System Simulation, 2019, 31(11): 2499-2508.

参考文献

[1] Qian Yong.Studies on the Attitude Determination and Control System of High Precision Three-axis Stabilized Satellite[D]. Xi'an: Northwestern Polytechnical University, 2002.
[2] Liu Xinyue.Research on Fault Diagnosis Method of Satellite Control System Based on Deep Learning[D]. Bejing: BeiHang University, 2018.
[3] Xiao C, Jiao Z, Sun J T, et al.Fault prediction of variable pitch system of wind turbine based on wavelet BP neural network[J]. Renewable Energy Resources (S1671-5292), 2017, 35(6): 893-899.
[4] Li Q, Yu J Y, Mu B C, et al.BP neural network prediction of the mechanical properties of porous NiTi shape memory alloy prepared by thermal explosion reaction[J]. Materials Science and Engineering: A (S0921-5093), 2006, 419(1-2): 214-217.
[5] Shen X Y, Zhang F, Lü H T, et al.Prediction of Entering Percentage into Expressway Service Areas Based on Wavelet Neural Networks and Genetic Algorithms[J]. IEEE Access (S2169-3536), 2019, 7: 54562-54574
[6] Wang J Y, Wang Z, Li J F, et al.Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis[Z]. Computer Science, Statistics, 2018.
[7] Zhang R W.Attitude dynamics and control of satellite orbit[M]. Bejing: Beihang University Press, 1998.
[8] Wang M L.Research on fault diagnosis of satellite control system[D]. Bejing: BeiHang University, 2017.
[9] Shi S H, Wang T Q, Chu X W, et al.A DAG Model of Synchronous Stochastic Gradient Descent in Distributed Deep Learning[C]. 2018 IEEE 24^th International Conference on Parallel and Distributed Systems (ICPADS) Parallel and Distributed Systems (ICPADS), 2018 IEEE 24th International Conference on: 425-432 Dec, 2018.
[10] Luo P.Study on wavelet neural network based on back propagation algorithm[J]. Information Technology (S1009-2552), 2012(11): 48-51, 56.
[11] Ingrid Daubechies.1992. Ten lectures on wavelets. SIAM.
[12] Yara Rizk, Mariette Awad.On Extreme Learning Machines in Sequential and Time Series Prediction: A Non-Iterative and Approximate Training Algorithm for Recurrent Neural Networks[J]. Neurocomputing(S0925-2312), 2018.
[13] Gers F A, Schmidhuber J, Cummins F.Learning to forget: continual prediction with LSTM[C]. Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on. IET, 2002: 2451.
[14] Wöllmer M, Kaiser M, Eyben F, et al.LSTM-Modeling of continuous emotions in an audiovisual affect recognition framework[J]. Image & Vision Computing (S0262-8856), 2013, 31(2): 153-163.

[1]	孙晓安, 栾小丽, 刘飞. 基于智能优化灰色模型的电子固废预测[J]. 系统仿真学报, 2022, 34(3): 536-542.
[2]	魏娟, 游磊, 郭阳勇, 唐志海. 基于小波神经网络的多楼层疏散模型[J]. 系统仿真学报, 2022, 34(2): 269-277.
[3]	王海超, 尹勇. 航海模拟器中人员落水救助操纵智能化评估[J]. 系统仿真学报, 2021, 33(11): 2647-2655.
[4]	于军琪, 井文强, 赵安军, 任延欢, 周梦, 黄馨乐, 杨雪. 基于改进PSO-BP算法的冷负荷预测模型[J]. 系统仿真学报, 2021, 33(1): 54-61.
[5]	唐少虎, 周进, 尚春琳, 郑国荣. 降雨情景下城市道路交通信号控制优化模型与方法[J]. 系统仿真学报, 2020, 32(2): 149-156.
[6]	杨文峰, 王艳, 纪志成. 基于RF-GA-BP神经网络的N-乙酰氨基葡萄糖含量预测[J]. 系统仿真学报, 2020, 32(10): 2034-2040.
[7]	贾立山, 刘喆, 孙毅. 基于RMBP神经网络的飞机电气故障智能诊断[J]. 系统仿真学报, 2018, 30(9): 3493-3501.
[8]	孔红山, 郁滨. 一种基于BP神经网络的VIRE改进算法研究[J]. 系统仿真学报, 2018, 30(9): 3586-3595.
[9]	沈艳霞, 苗贝贝. 三电平逆变器的开关管开路故障诊断策略[J]. 系统仿真学报, 2018, 30(8): 3058-3065.
[10]	王修岩, 刘艳敏, 张革文, 李宗帅, 林家泉. 基于PSO和CRO联合算法的飞机客舱能耗预测[J]. 系统仿真学报, 2018, 30(8): 3074-3081.
[11]	陶文华, 袁正波. 焦炭质量的DE-BP神经网络预测模型研究[J]. 系统仿真学报, 2018, 30(5): 1650-1656.
[12]	白书华, 况明星. 基于PSO-GA-BP神经网络的林火预测设计与研究[J]. 系统仿真学报, 2018, 30(5): 1739-1748.
[13]	陆营波, 钱晓超, 陈伟, 何舒, 陆志沣. 数据驱动的装备效能评估模型构建方法研究[J]. 系统仿真学报, 2018, 30(12): 4587-4595.
[14]	刘经纬, 周瑞, 赵辉, 朱敏玲, 孟祥花, 张宇豪. 预测小波神经网络智能控制系统仿真研究[J]. 系统仿真学报, 2018, 30(10): 3770-3780.
[15]	刘增良, 周松林, 周同旭. 基于IDE-WNN的短期风电功率预测及概率评估[J]. 系统仿真学报, 2016, 28(2): 476-482.

基于神经网络的卫星姿控系统故障预测

Fault Prediction of Satellite Attitude Control System Based on Neural Network

PDF (PC)

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

本文评价