基于DWT和双通道LSTM的卫星电池阵电流预测方法

doi:10.7523/j.issn.2021.0028

中国科学院大学学报 ›› 2023, Vol. 40 ›› Issue (3): 415-421.DOI: 10.7523/j.issn.2021.0028

基于DWT和双通道LSTM的卫星电池阵电流预测方法

何利健^1,2, 张锐^1,2, 林晓冬¹

1. 中国科学院微小卫星创新研究院, 上海;
2. 中国科学院大学, 北京 100049

收稿日期:2021-01-04 修回日期:2021-03-23 发布日期:2023-05-13
通讯作者: 张锐,E-mail:acumen_zhang@163.com

Satellite battery array current prediction method based on DWT and dual-channel LSTM

HE Lijian^1,2, ZHANG Rui^1,2, LIN Xiaodong¹

1. Innovation Academy for Microsatellites, Chinese Academy of Sciences, Shanghai;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2021-01-04 Revised:2021-03-23 Published:2023-05-13

摘要/Abstract

摘要： 卫星太阳能电池阵输入电流受地球反照、卫星反照等多方面影响，会产生不同频率的波动起伏，造成预测精度不足，针对该问题提出一种基于离散小波变换(DWT)和长短期记忆网络(LSTM)的电流数据预测方法。首先对电流信号进行归一化，其次使用DWT对遥测信号进行小波分解，获取信号的多层高低频小波系数，提高信号数据特征，然后通过双通道LSTM进行特征学习，预测出各层小波系数，最后通过对预测出来的小波系数进行信号重构并反归一化获得最终预测信号。通过使用某在轨卫星太阳能电池阵电流遥测数据对预测模型进行验证，结果表明提出的方法相对于传统LSTM模型具有更好的预测精度，平均绝对误差减少16.4%，均方根误差减少29.9%，相关系数提高3.2%。

关键词: 长短期记忆网络, 离散小波变换, 遥测数据, 太阳电池阵, 预测模型

Abstract: The input current of the satellite solar array is affected by the earth albedo, satellite albedo, etc., which will produce fluctuations of different frequencies, resulting in insufficient prediction accuracy. To solve this problem, a current data prediction method based on discrete wavelet transform (DWT) and long-term short-term memory (LSTM) is proposed. First, the signal is normalized, and then discrete wavelet transform is used to decompose the telemetry signal, to obtain the multi-layer high and low-frequency wavelet coefficients of the signal to improve the signal data characteristics, and then use dual-channel LSTM is used to perform feature learning to predict each layer of wavelet coefficients, and finally the final prediction signal is obtained by reconstructing and de-normalizing the predicted wavelet coefficients. The model is verified by using the current telemetry data of an on-orbit satellite solar array. The results show that the proposed method has better prediction accuracy than traditional LSTM. MAE is reduced by 16.4%, RMSE is reduced by 29.9%, and R is improved by 3.2%.

Key words: long short-term memory, discrete wavelet transform, telemetry data, solar array, prediction model

中图分类号:

TP391

何利健, 张锐, 林晓冬. 基于DWT和双通道LSTM的卫星电池阵电流预测方法[J]. 中国科学院大学学报, 2023, 40(3): 415-421.

HE Lijian, ZHANG Rui, LIN Xiaodong. Satellite battery array current prediction method based on DWT and dual-channel LSTM[J]. Journal of University of Chinese Academy of Sciences, 2023, 40(3): 415-421.

参考文献

[1] 王嘉轶, 闻新. 航天器故障诊断技术的研究现状与进展[J]. 航空兵器, 2016(5):71-76.DOI:10.19297/j.cnki.41-1228/tj.2016.05.014.
[2] 董静怡, 庞景月, 彭宇, 等. 集成LSTM的航天器遥测数据异常检测方法[J]. 仪器仪表学报, 2019, 40(7):22-29.DOI:10.19650/j.cnki.cjsi.J1904832.
[3] 彭喜元, 庞景月, 彭宇, 等. 航天器遥测数据异常检测综述[J]. 仪器仪表学报, 2016, 37(9):1929-1945.DOI:10.19650/j.cnki.cjsi.2016.09.002.
[4] 修春波, 任晓, 李艳晴, 等. 基于卡尔曼滤波的风速序列短期预测方法[J]. 电工技术学报, 2014, 29(2):253-259.DOI:10.19595/j.cnki.1000-6753.tces.2014.02.031.
[5] 刘星, 吕孝雷. 基于卡尔曼滤波的PS-InSAR地表形变预测方法[J]. 中国科学院大学学报, 2017, 34(6):743-750.DOI:10.7523/j.issn.2095-6134.2017.06.011.
[6] Huang R, Huang T, Gadh R, et al. Solar generation prediction using the ARMA model in a laboratory-level micro-grid[C]//2012 IEEE Third International Conference on Smart Grid Communications (SmartGridComm). Tainan, Taiwan, China:IEEE, 2012:528-533.DOI:10.1109/SmartGridComm.2012.6486039.
[7] Anwar M Y, Lewnard J A, Parikh S, et al. Time series analysis of malaria in Afghanistan:using ARIMA models to predict future trends in incidence[J]. Malaria Journal, 2016, 15(1):566.DOI:10.1186/s12936-016-1602-1.
[8] Vui C S, Soon G K, On C K, et al. A review of stock market prediction with Artificial neural network (ANN)[C]//2013 IEEE International Conference on Control System, Computing and Engineering. Penang, Malaysia:IEEE, 2013:477-482.DOI:10.1109/ICCSCE.2013.6720012.
[9] Ma D L, Zhou T, Chen J, et al. Supercritical water heat transfer coefficient prediction analysis based on BP neural network[J]. Nuclear Engineering and Design, 2017, 320:400-408.DOI:10.1016/j.nucengdes.2017.06.013.
[10] 田玮, 朱廷劭. 基于深度学习的微博用户自杀风险预测[J]. 中国科学院大学学报, 2018, 35(1):131-136.DOI:10.7523/j.issn.2095-6134.2018.01.018.
[11] 王剑非, 姜斌, 冒泽慧. 基于LSSVM的卫星姿态控制系统故障诊断[J]. 控制工程, 2008, 15(3):334-336,341.DOI:10.14107/j.cnki.kzgc.2008.03.010.
[12] Hundman K, Constantinou V, Laporte C, et al. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, NY, USA:ACM, 2018:387-395.DOI:10.1145/3219819.3219845.
[13] Li T Y, Comer M, Delp E, et al. A stacked predictor and dynamic thresholding algorithm for anomaly detection in spacecraft[C]//2019 IEEE Military Communications Conference (MILCOM 2019). Norfolk, VA, USA:IEEE, 2019:165-170.DOI:10.1109/MILCOM47813.2019.9021055.
[14] 简献忠, 顾洪志, 王如志. 一种基于双通道CNN和LSTM的短期光伏功率预测方法[J]. 电力科学与工程, 2019, 35(5):7-11.DOI:10.3969/j.ISSN.1672-0792.2019.05.002.
[15] 孙铭, 魏守科, 王莹洁, 等. 基于小波分解的LSTM水质预测模型[J]. 计算机系统应用, 2020, 29(12):55-63.DOI:10.15888/j.cnki.cas.007695.
[16] 何哲祥, 李雷. 基于小波变换和LSTM的大气污染物浓度预测模型[J]. 环境工程, (2020-11-27)[2021-03-19]. http://kns.cnki.net/kcms/detail/11.2097.X.20201126.1858.002.html.
[17] 杨梅, 李忠, 吴昊. 基于多尺度时间特征的LSTM短期负荷预测[J]. 控制工程, 2022,29(9):1722-1728. DOI:10.14107/j.cnki.kzgc.20200542.

基于DWT和双通道LSTM的卫星电池阵电流预测方法

Satellite battery array current prediction method based on DWT and dual-channel LSTM

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	曹州, 刘士彬, 马勇, 姚武韬, 姜丽媛. 一种联合光谱-对象-时间特征的遥感影像变化检测方法[J]. 中国科学院大学学报, 2022, 39(1): 102-109.
[2]	唐思琦, 韩丛英, 郭田德. 基于机器学习的点集匹配算法[J]. 中国科学院大学学报, 2020, 37(4): 450-457.
[3]	侯启槟, 王阳生, 黄向生, 周晓旭. 结合EZW和AES的图像加密机制[J]. 中国科学院大学学报, 2004, 21(1): 119-124.