基于ILLE和SVM的卫星执行机构系统故障检测与定位
|
摘要
针对某超高指向精度要求的卫星平台,采用增量式局部线性嵌入(ILLE)与支持向量机(SVM)结合的方法,研究系统配置的多组磁伺服机构的故障检测与故障定位技术。在分析执行机构故障模式以及故障影响的基础上,采用LLE算法实时提取并更新与故障相关的卫星姿态控制系统高维信息,对其进行降维及特征提取,实现执行机构系统故障检测。当检测到故障时,提取执行机构系统输入输出信息,利用支持向量机(SVM)方法进行故障定位。该方法无需采集离线数据生成样本集,直接利用卫星姿控系统产生的在线故障特征数据集进行故障检测,并能根据故障检测结果,有效地实现卫星姿控系统执行机构的故障定位。算例仿真结果验证了所提方法的有效性。
In consideration of a satellite platform with requirements of ultra-high pointing accuracy,a fault diagnosis method based on incremental local linear embedding( ILLE) and support vector machine( SVM) is used to study the fault detection and fault location technology of multiple sets of satellite-borne magnetic servo mechanisms. Based on the analysis of the failure mode of the actuator and the impact of the failure,the LLE algorithm is used to extract and update the high-dimensional information of the satellite attitude control system related to the fault in real time,and the dimension and feature extraction is reduced to realize fault detection of the actuator system. When a fault is detected,a method based on SVM is proposed with input and output information of the actuator system to realize fault location. Without collecting offline data to generate a sample set,the online fault feature data set is directly used in this method,which is generated by the satellite attitude control system to perform fault detection. And fault of the satellite attitude control system is effectively located according to fault detection results. Simulation results demonstrate the effectiveness of the proposed method.
In consideration of a satellite platform with requirements of ultra-high pointing accuracy,a fault diagnosis method based on incremental local linear embedding( ILLE) and support vector machine( SVM) is used to study the fault detection and fault location technology of multiple sets of satellite-borne magnetic servo mechanisms. Based on the analysis of the failure mode of the actuator and the impact of the failure,the LLE algorithm is used to extract and update the high-dimensional information of the satellite attitude control system related to the fault in real time,and the dimension and feature extraction is reduced to realize fault detection of the actuator system. When a fault is detected,a method based on SVM is proposed with input and output information of the actuator system to realize fault location. Without collecting offline data to generate a sample set,the online fault feature data set is directly used in this method,which is generated by the satellite attitude control system to perform fault detection. And fault of the satellite attitude control system is effectively located according to fault detection results. Simulation results demonstrate the effectiveness of the proposed method.
引文
[1]陈嘉文,程月华,姜斌,等.面向任务约束的航天器姿控系统在轨重构算法[J].宇航学报,2017,38(9):989-997.(Chen J W,Cheng Y H,Jiang B,et al.Mission-Constrained Spacecraft Attitude Control System On-Orbit Reconfiguration Algorithm[J].Journal of Astronautics,2017,38(9):989-997.)
[2]Ma Y,Jiang B,Gang T.Adaptive Actuator Failure I-dentification for Microsatellites Under Closed-Loop Control[J].IEEE Transactions on Control Systems Technology,2015,23(3):910-923.
[3]傅艳萍,程月华,姜斌.基于输入受限的轨控期间挠性卫星容错控制研究[J].航天控制,2012,30(3):38-44.(Fu Y P,Cheng Y H,Jiang B.Fault-tolerant Control Under Constrained Input for Flexible Satellite Attitude Control System During Orbit Control[J].Aerospace Control,2012,30(3):38-44.)
[4]Wang C,Lu N,Wang S,et al.Dynamic Long ShortTerm Memory Neural-Network-Based Indirect Remaining-Useful-Life Prognosis for Satellite Lithium-Ion Battery[J].Applied Sciences,2018,8(11):2078.
[5]Peng Y,Jia S Z,Feng X H,et al.Telemetry Fault Detection for Meteorological Satellite Based on PCA[C]//16th International Symposium on Communications and Information Technologies(ISCIT).IEEE,Qingdao,China,September 26-28,2016,357-361.
[6]Wang H J,Wang H F,Ji Y J.Orbit Identification Method Based on ISOMAP for Rotor System Fault Diagnosis[C]//2013 IEEE 11th International Conference on Electronic Measurement and Instruments(ICEMI).IEEE,Harbin,China,August 16-19,2013,668-671.
[7]Cheng Y H,Hu G F,Lu N Y,et al.Fault Detection Based on Incremental Locally Linear Embedding for Satellite TX-I[J].Transactions of Nanjing University of Aeronautics and Astronautics,2015,32(6):600-609.
[8]Miao A,Ge Z,Song Z,et al.Nonlocal Structure Constrained Neighborhood Preserving Embedding Model and Its Application for Fault Detection[J].Chemometrics and Intelligent Laboratory Systems,2015,142:184-196.
[9]王涛.基于流形学习的卫星姿态控制系统故障检测技术研究[D].南京航空航天大学,2015.(Wang T.Research on Manifold Learning-Based Fault Detection for Satellite Attitude Control Systems[D].Nanjing University of Aeronautics and Astronautics,2015.)
[10]Mousavi S,Khorasani K.Fault Detection of Reaction Wheels in Attitude Control Subsystem of Formation Flying Satellites[J].International Journal of Intelligent Unmanned Systems,2014,2(1):2-26.
[11]陈辛,魏炳翌,闻新.基于支持向量机的卫星执行机构故障诊断研究[J].中国空间科学技术,2018,38(2):47-55.(Chen X,Wei B Y,Wen X.Study of Support Vector Machine Based Faults Diagnosis for Satellite’s Actuators[J].Chinese Space Science and Technology,2018,38(2):47-55.)
[12]张伟,廖鹤,袁金如,等.动静隔离、主从协同控制的双超卫星平台设计[J].上海航天,2014,31(5):7-11.(Zhang W,Liao H,Yuan J R,et al.Design of an Active-Quiet Isolated and Master-Slave Coordination Controlled Dual-Super Satellite Platform[J].Aerospace Shanghai,2014,31(5):7-11.)
[13]李明.基于多元统计分析的故障诊断方法及其应用研究[D].山东大学,2006.(Li M.Research on Fault Diagnosis Method Based on Multivariate Statistical Analysis and Its Application[D].Shandong University,2006.)
[14]马笑潇,黄席樾,柴毅.基于SVM的二叉树多类分类算法及其在故障诊断中的应用[J].控制与决策,2003,18(3):272-276.(Ma X X,Huang X Y,Chai Y.2PTMC Classification Algorithm Based on Support Vector Machines and Its Application to Fault Diagnosis[J].Control and Decision,2003,18(3):272-276.)
[2]Ma Y,Jiang B,Gang T.Adaptive Actuator Failure I-dentification for Microsatellites Under Closed-Loop Control[J].IEEE Transactions on Control Systems Technology,2015,23(3):910-923.
[3]傅艳萍,程月华,姜斌.基于输入受限的轨控期间挠性卫星容错控制研究[J].航天控制,2012,30(3):38-44.(Fu Y P,Cheng Y H,Jiang B.Fault-tolerant Control Under Constrained Input for Flexible Satellite Attitude Control System During Orbit Control[J].Aerospace Control,2012,30(3):38-44.)
[4]Wang C,Lu N,Wang S,et al.Dynamic Long ShortTerm Memory Neural-Network-Based Indirect Remaining-Useful-Life Prognosis for Satellite Lithium-Ion Battery[J].Applied Sciences,2018,8(11):2078.
[5]Peng Y,Jia S Z,Feng X H,et al.Telemetry Fault Detection for Meteorological Satellite Based on PCA[C]//16th International Symposium on Communications and Information Technologies(ISCIT).IEEE,Qingdao,China,September 26-28,2016,357-361.
[6]Wang H J,Wang H F,Ji Y J.Orbit Identification Method Based on ISOMAP for Rotor System Fault Diagnosis[C]//2013 IEEE 11th International Conference on Electronic Measurement and Instruments(ICEMI).IEEE,Harbin,China,August 16-19,2013,668-671.
[7]Cheng Y H,Hu G F,Lu N Y,et al.Fault Detection Based on Incremental Locally Linear Embedding for Satellite TX-I[J].Transactions of Nanjing University of Aeronautics and Astronautics,2015,32(6):600-609.
[8]Miao A,Ge Z,Song Z,et al.Nonlocal Structure Constrained Neighborhood Preserving Embedding Model and Its Application for Fault Detection[J].Chemometrics and Intelligent Laboratory Systems,2015,142:184-196.
[9]王涛.基于流形学习的卫星姿态控制系统故障检测技术研究[D].南京航空航天大学,2015.(Wang T.Research on Manifold Learning-Based Fault Detection for Satellite Attitude Control Systems[D].Nanjing University of Aeronautics and Astronautics,2015.)
[10]Mousavi S,Khorasani K.Fault Detection of Reaction Wheels in Attitude Control Subsystem of Formation Flying Satellites[J].International Journal of Intelligent Unmanned Systems,2014,2(1):2-26.
[11]陈辛,魏炳翌,闻新.基于支持向量机的卫星执行机构故障诊断研究[J].中国空间科学技术,2018,38(2):47-55.(Chen X,Wei B Y,Wen X.Study of Support Vector Machine Based Faults Diagnosis for Satellite’s Actuators[J].Chinese Space Science and Technology,2018,38(2):47-55.)
[12]张伟,廖鹤,袁金如,等.动静隔离、主从协同控制的双超卫星平台设计[J].上海航天,2014,31(5):7-11.(Zhang W,Liao H,Yuan J R,et al.Design of an Active-Quiet Isolated and Master-Slave Coordination Controlled Dual-Super Satellite Platform[J].Aerospace Shanghai,2014,31(5):7-11.)
[13]李明.基于多元统计分析的故障诊断方法及其应用研究[D].山东大学,2006.(Li M.Research on Fault Diagnosis Method Based on Multivariate Statistical Analysis and Its Application[D].Shandong University,2006.)
[14]马笑潇,黄席樾,柴毅.基于SVM的二叉树多类分类算法及其在故障诊断中的应用[J].控制与决策,2003,18(3):272-276.(Ma X X,Huang X Y,Chai Y.2PTMC Classification Algorithm Based on Support Vector Machines and Its Application to Fault Diagnosis[J].Control and Decision,2003,18(3):272-276.)
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |