基于功耗残差的航天器CMG退化特征提取方法

田利梅; 龚梦彤; 唐荻音; 韩丹阳; 于劲松; 李春伟

doi:10.13700/j.bh.1001-5965.2021.0060

基于功耗残差的航天器CMG退化特征提取方法

doi: 10.13700/j.bh.1001-5965.2021.0060

1.
北京控制工程研究所, 北京 100094
2.
北京航空航天大学自动化科学与电气工程学院, 北京 100083

基金项目:

国家自然科学基金 71701008

国家商用飞机制造工程技术研究中心创新基金 COMAC-SFGS-2019-261

详细信息

通讯作者:
唐荻音, E-mail: tangdiyin@buaa.edu.cn

中图分类号: V44;TP202⁺.1
计量
- 文章访问数: 303
- HTML全文浏览量: 105
- PDF下载量: 31
- 被引次数: 0
出版历程
- 收稿日期: 2021-02-03
- 录用日期: 2021-04-04
- 网络出版日期: 2021-04-12
- 整期出版日期: 2022-10-20

Degradation indicator extraction for aerospace CMG based on power consumption analysis

1.
Beijing Institute of Control Engineering, Beijing 100094, China
2.
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100083, China

Funds:

National Natural Science Foundation of China 71701008

Fund of National Engineering and Research Center for Commercial Aircraft Manufacturing COMAC-SFGS-2019-261

More Information

Corresponding author: TANG Diyin, E-mail: tangdiyin@buaa.edu.cn

摘要

摘要:
为实现航天器控制力矩陀螺（CMG）性能退化状态评估，提出了一种基于卷积神经网络（CNN）与功耗残差的CMG退化特征提取方法。由于CMG控制系统对高速转子运动状态的高精准控制，CMG退化特征难以从转子运动状态数据中直接提取。针对该问题，从转子系统的能量损耗角度出发，通过分析CMG工作机理确定了影响单位时间内转子电机功耗的变量，并通过CNN建立了CMG运行状态参数与电机功耗之间的映射。将退化状态下电机实际功耗与模型输出的残差作为退化特征对CMG退化状态进行评价。通过某型号CMG的加速寿命实验数据进行验证，结果表明：构建的退化特征能够表征CMG转子轴承的性能退化情况，从而为CMG状态监测和故障预警提供参考。
- 控制力矩陀螺(CMG) /
- 滚动轴承 /
- 退化特征 /
- 卷积神经网络(CNN) /
- 功耗残差
Abstract:
Control moment gyro (CMG) is the actuator for the attitude control of large spacecraft. In order to evaluate the performance degradation state of CMG, a convolutional neural network (CNN) and residual power consumption-based degradation feature extraction method is proposed. The high-precision control of the CMG control system makes it difficult to extract degradation features from the operational state of the CMG rotor. To solve this problem, a CNN model is introduced to establish the mapping between CMG operating state parameters and motor power consumption, and the degradation feature is defined as the residual error between the model output and actual power consumption of the motor in the degraded state. For approach validation, an accelerated life test dataset of a real CMG was used. The results show that the constructed degradation feature can reflect the performance degradation of the CMG rotor bearing.
- control moment gyro (CMG) /
- rolling bearing /
- degradation features /
- convolutional neural network (CNN) /
- residual power consumption

HTML全文

图 1 SGCMG结构简图

Figure 1. Structure sketch of the SGCMG

下载: 全尺寸图片幻灯片

图 2 CNN网络结构示意图

Figure 2. Architecture of CNN network

下载: 全尺寸图片幻灯片

图 3 SGCMG实验平台

Figure 3. Experiment platform of SGCMG

下载: 全尺寸图片幻灯片

图 4 遥测数据示例

Figure 4. Raw data telemetry signals

下载: 全尺寸图片幻灯片

图 5 模型训练与功耗估计结果

Figure 5. Results of model training and power

下载: 全尺寸图片幻灯片

图 6 转子电机功耗残差

Figure 6. Residual power consumption of rotor motor

下载: 全尺寸图片幻灯片

表 1 退化特征性能对比

Table 1. Comparison of degradation indicators performance

工况	特征	Tred	Mon	HM
	均值	0.696 1	0.025 3	0.226 5
	均方根	0.696 1	0.025 3	0.226 5
	峰峰值	0.060 4	0.007 5	0.023 4
	偏度	0.024 4	0.002 5	0.009 1
	峭度	0.015 5	0.001 9	0.006 0
工况1	波形指数	0.006 7	0.001 4	0.003 0
	峰值指数	0.044 4	0.005 3	0.017 0
	裕度指数	0.044 4	0.006 4	0.017 8
	峭度指数	0.046 0	0.003 1	0.015 9
	PCA	0.605 8	0.034 2	0.205 7
	功耗残差	0.942 5	0.003 1	0.284 9
	均值	0.134 2	0.002 0	0.041 6
	均方根	0.134 2	0.002 0	0.041 6
	峰峰值	0.027 8	0.012 4	0.017 0
	偏度	0.004 8	0.012 4	0.010 1
	峭度	0.020 7	0.005 9	0.010 3
工况2	波形指数	0.012 9	0.024 2	0.020 8
	峰值指数	0.018 1	0.005 9	0.009 6
	裕度指数	0.018 1	0.005 9	0.009 6
	峭度指数	0.008 5	0.007 2	0.007 6
	PCA	0.214 8	0.005 9	0.068 6
	功耗残差	0.843 1	0.009 8	0.259 8

下载: 导出CSV

参考文献(20)

[1]	ZHENG S, HAN B, GUO L. Composite hierarchical antidisturbance control for magnetic bearing system subject to multiple external disturbances[J]. IEEE Transactions on Industrial Electronics, 2014, 61(12): 7004-7012. doi: 10.1109/TIE.2014.2316226
[2]	LEI Y, LI N, GUO L, et al. Machinery health prognostics: A systematic review from data acquisition to RUL prediction[J]. Mechanical Systems and Signal Processing, 2018, 104: 799-834. doi: 10.1016/j.ymssp.2017.11.016
[3]	WANG D, TSUI K L, MIAO Q. Prognostics and health management: A review of vibration based bearing and gear health indicators[J]. IEEE Access, 2017, 6: 665-676.
[4]	HUANG Z, XU Z, KE X, et al. Remaining useful life prediction for an adaptive skew-Wiener process model[J]. Mechanical Systems and Signal Processing, 2017, 87: 294-306. doi: 10.1016/j.ymssp.2016.10.027
[5]	GUO L, LI N, JIA F, et al. A recurrent neural network based health indicator for remaining useful life prediction of bearings[J]. Neurocomputing, 2017, 240: 98-109. doi: 10.1016/j.neucom.2017.02.045
[6]	JUNG J H, LEE J J, KWON B H. Online diagnosis of induction motors using MCSA[J]. IEEE Transactions on Industrial Electronics, 2006, 53(6): 1842-1852. doi: 10.1109/TIE.2006.885131
[7]	HAN B, ZHENG S, WANG Z, et al. Design, modeling, fabrication, and test of a large-scale single-gimbal magnetically suspended control moment gyro[J]. IEEE Transactions on Industrial Electronics, 2015, 62(12): 7424-7435. doi: 10.1109/TIE.2015.2459052
[8]	LIU J, YAN Z, SHAO Y. An investigation for the friction torque of a needle roller bearing with the roundness error[J]. Mechanism and Machine Theory, 2018, 121: 259-272. doi: 10.1016/j.mechmachtheory.2017.10.028
[9]	STAMMLER M, SCHWACK F, BADER N, et al. Friction torque of wind-turbine pitch bearings-comparison of experimental results with available models[J]. Wind Energy Science, 2018, 3(1): 97-105. doi: 10.5194/wes-3-97-2018
[10]	HEIBERG C. A practical approach to modeling single-gimbal control momentum gyroscopes in agile spacecraft: AIAA-2000-4545[R]. Reston: AIAA, 2000.
[11]	LI H, ZHENG S, NING X. Precise control for gimbal system of double gimbal control moment gyro based on cascade extended state observer[J]. IEEE Transactions on Industrial Electronics, 2017, 64(6): 4653-4661. doi: 10.1109/TIE.2017.2674585
[12]	ATALLAH K, ZHU Z Q, HOWE D. An improved method for predicting iron losses in brushless permanent magnet DC drives[J]. IEEE Transactions on Magnetics, 1992, 28(5): 2997-2999. doi: 10.1109/20.179696
[13]	SHIGEMATSU K, OYAMA J, HIGUCHI T, et al. The study of eddy current in rotor and circuit coupling analysis for small size and ultra-high speed motor[C]//The 4th International Power Electronics and Motion Control Conference. Piscataway: IEEE Press, 2004: 275-279.
[14]	WEN L, LI X, GAO L, et al. A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5990-5998. doi: 10.1109/TIE.2017.2774777
[15]	INCE T, KIRANYAZ S, EREN L, et al. Real-time motor fault detection by 1-D convolutional neural networks[J]. IEEE Transactions on Industrial Electronics, 2016, 63(11): 7067-7075. doi: 10.1109/TIE.2016.2582729
[16]	ZHANG B, ZHANG L, XU J. Degradation feature selection for remaining useful life prediction of rolling element bearings[J]. Quality and Reliability Engineering International, 2016, 32(2): 547-554. doi: 10.1002/qre.1771
[17]	JAVED K, GOURIVEAU R, ZERHOUNI N, et al. Enabling health monitoring approach based on vibration data for accurate prognostics[J]. IEEE Transactions on Industrial Electronics, 2015, 62(1): 647-656. doi: 10.1109/TIE.2014.2327917
[18]	WANG Y, PENG Y, ZI Y, et al. A two-stage data-driven-based prognostic approach for bearing degradation problem[J]. IEEE Transactions on Industrial Informatics, 2016, 12(3): 924-932. doi: 10.1109/TII.2016.2535368
[19]	WIDODO A, YANG B S. Application of relevance vector machine and survival probability to machine degradation assessment[J]. Expert Systems with Applications, 2011, 38(3): 2592-2599. doi: 10.1016/j.eswa.2010.08.049
[20]	LE S K, FOULADIRAD M, BARROS A, et al. Remaining useful life estimation based on stochastic deterioration models: A comparative study[J]. Reliability Engineering & System Safety, 2013, 112: 165-175.