基于PCA和WPSVM的航天器电特性识别方法

李可; 刘祎; 杜少毅; 孙毅; 王浚

doi:10.13700/j.bh.1001-5965.2014.0482

基于PCA和WPSVM的航天器电特性识别方法

doi: 10.13700/j.bh.1001-5965.2014.0482

李可^1, ,,
刘祎¹,
杜少毅²,
孙毅³,
王浚¹

1.
北京航空航天大学航空科学与工程学院, 北京 100191
2. 西安交通大学人工智能与机器人研究所, 西安 710049
3. 中国空间技术研究院, 北京 100194

基金项目: 航空科学基金(2012XX1043); 中央高校基本科研业务费专项资金(YWF-14-HKXY-017)

详细信息

通讯作者:
李可(1980—),男,江苏徐州人,讲师,like@buaa.edu.cn,主要研究方向为智能控制、机器学习等.

中图分类号: TP391.4
计量
- 文章访问数: 789
- HTML全文浏览量: 156
- PDF下载量: 567
- 被引次数: 0
出版历程
- 收稿日期: 2014-07-31
- 修回日期: 2014-09-26
- 网络出版日期: 2015-07-20

Spacecraft electrical characteristics identification method based on PCA feature extraction and WPSVM

LI Ke^{1
, ,},
LIU Yi¹,
DU Shaoyi²,
SUN Yi³,
WANG Jun¹

1.
School of Aeronautic Science and Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
2. Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an 710049, China
3. China Academy of Space Technology, Beijing 100194, China

摘要

摘要: 针对航天器电特性监测系统识别过程中存在测试数据量大、特征维数高、样本少、计算速度慢和识别率低等问题,提出基于主成分分析(PCA)的特征提取和加权近似支持向量机(WPSVM)的在线故障诊断方法.实现了对信号故障特征的主成分分析、选择和提取,并对高维特征数据实现了降维,提高了航天器电特性在线故障诊断的准确性和速度.针对PCA中的结果选取问题,提出运用数据贡献度阈值进行数据截取的方法,有效地保证了数据的有效性与一致性.结果表明:该方法充分利用了航天器电特性监测系统的有用数据特征,有效提高了识别的精度,且计算时间较短,效率较高.
- 航天器 /
- 主成分分析(PCA) /
- 降维 /
- 小样本 /
- 支持向量机(SVM) /
- 电特性识别
Abstract: To solve the problems of large amount of unlabeled test data, high dimension characteristics, slow computing speed and low recognition rate during the spacecraft electrical characteristics identification process of monitoring system, an on-line identification algorithm based on principal component analysis (PCA) feature extraction and weighted proximal support vector machine (WPSVM) was proposed. The principal component analysis is used for feature selection and extraction during complex signal analysis process, to reduce the characteristics dimension and improve the speed of the spacecraft electrical on-line identification. In order to resolve the PCA results selection problem, our team put forward data capture contribution method by using threshold to capture data, effectively guarantee the validity and consistency of the data. The experimental results indicate that this method we proposed can get better spacecraft electrical characteristics data feature, improve the accuracy of identification, and shorten the compute-time with high efficiency at the same time.
- spacecraft /
- principal component analysis (PCA) /
- dimensional-reduction /
- small sample /
- support vector machine (SVM) /
- electrical characteristics identification

HTML全文

参考文献(15)

[1]	Steven R S. System identification technology modeling for nonintrusive load diagnostics[D].Cambridge: Massachusetts Institute of Technology, 2000.
[2]	Zadeh L A. Outline of a new approach to the analysis of complex systems and decision processes[J].IEEE Transactions on Systems, Man, and Cybernetics, 1973, 3(1): 28-44.
[3]	Chew H G, Bogner R E, Lim C C.Dual ν-support vector machine with error rate and training size biasing[C]//IEEE International Conference Acoustics Speech Signal Processing.Piscataway, NJ: IEEE Press, 2001, 2: 1269-1272.
[4]	杜林, 刘伟明, 王有元.基于CPLD的电网过电压变频数据采集卡设计[J].高电压技术, 2008, 34(8): 1589-1593. Du L, Liu W M, Wang Y Y.Data acquisition card with variable sampling speed for monitoring overvoltage based on CPLD[J].High Voltage Engineering, 2008, 34(8): 1589-1593(in Chinese).
[5]	吴昊, 肖先勇.小波能量谱和神经元网络法识别雷击与短路故障[J].高电压技术, 2007, 33(10): 189-193. Wu H, Xiao X Y.Lightning strike and fault identification by the wavelet energy spectrum and neural network method[J].High Voltage Engineering, 2007, 33(10): 189-193(in Chinese).
[6]	Huang J S, Negnevitsky M, Nguyen D T.A neural-fuzzy classifier for recognition of power quality disturbances[J].IEEE Transactions on Power Delivery, 2002, 17(2): 609-616.
[7]	王钢, 李海峰, 赵建仓, 等.基于小波多尺度分析的输电线路直击雷暂态识别[J].中国电机工程学报, 2004, 24(4): 358-364. Wang G, Li H F, Zhao J C, et al.Identification of transients on transmission lines caused by direct lighting strokes based on multiresolution signal decomposition[J].Proceedings of the CSEE, 2004, 24(4): 358-364(in Chinese).
[8]	Chien S, Sherwood R, Tran D, et al.Using autonomy flight software to improve science return on Earth Observing One[J].Journal of Aerospace Computing, Information, and Communication, 2005, 2(4): 196-216.
[9]	李可, 刘旺开, 王浚.专家-模糊PID在低速风洞风速控制系统中的应用[J].北京航空航天大学学报, 2007, 33(12): 1387-1390. Li K, Liu W K, Wang J.Parameters self-tuning fuzzy-PID combined with expert control on wind velocity control system of wind tunnels at home[J]. Journal of Beijing University of Aeronautics and Astronautics, 2007, 33(12): 1387-1390(in Chinese).
[10]	Li K, Liu W K, Wang J, et al.An intelligent control method for a large multi-parameter environmental simulation cabin[J].Chinese Journal of Aeronautics, 2013, 26(6): 1360-1369.
[11]	李可, 庞丽萍, 刘旺开, 等. 环境模拟舱体的建模仿真及控制方法[J].北京航空航天大学学报, 2007, 33(5): 535-538. Li K, Pang L P, Liu W K, et al.System model simulation andcontrol method used in environmental simulation chambers[J].Journal of Beijing University of Aeronautics and Astronautics, 2007, 33(5): 535-538(in Chinese).
[12]	Huang S H, Kothamasu R, Shiralkar Y C, et al.Prediction of plastic preform temperature profile and modeling perspective[J].International Journal of Manufacturing Science and Technology, 2003, 4(2): 56-83.
[13]	邓乃扬, 田英杰. 数据挖掘中的新方法——支持向量机[M].北京: 科学出版社, 2004: 189-193. Deng N Y, Tian Y J.A new method of data mining: SVM[M].Beijing: Science Press, 2004: 189-193(in Chinese).
[14]	Witten I H, Frank E.Data mining: Practical machine learning tools and techniques[M].2nd ed.San Francisco: Morgan Kaufmann, 2005: 36-39.
[15]	Zhu X, Ye J, Zhang X.A fixed-point nonlinear PCA algorithm for blind source separation[J].Neurocomputing, 2005, 69(1): 264-272.