在轨飞轮故障诊断混合框架设计

赵琳; 王艺鹏; 郝勇

doi:10.3788/OPE.20182607.1728

您当前的位置：

首页 >

文章列表页 >

在轨飞轮故障诊断混合框架设计

微纳技术与精密机械 | 更新时间：2020-08-13

- 在轨飞轮故障诊断混合框架设计
- Design of hybrid frame for on-orbit flywheel fault diagnosis
- 光学精密工程 2018年26卷第7期页码：1728-1740
- 作者机构：
  
  哈尔滨工程大学自动化学院, 黑龙江哈尔滨 150001
- 作者简介：
  
  [ "赵琳(1968-), 男, 黑龙江哈尔滨人, 教授, 博士生导师, 主要从事惯性导航技术、卫星导航技术、组合导航技术。E-mail:zhaolin@hrbeu.edu.cn" ]
  [ "王艺鹏(1990-), 男, 河北石家庄人, 博士研究生, 2010年于哈尔滨工程大学获得学士学位, 主要人工智能, 系统故障诊断等方面研究。E-mail:wangyipeng@hrbeu.edu.cn" ]
  [ "郝勇(1979-), 男, 吉林吉林市人, 工学博士, 助理研究员, 主要从事飞行器控制与任务规划等方面研究, E-mail:haoyong@hrbeu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金资助项目(61773132);黑龙江自然科学基金面上资助项目(F2017005);中央高校基本科研业务费(HEUCFP201768)
- DOI：10.3788/OPE.20182607.1728
  中图分类号： V9
- 收稿日期：2017-12-15，
  
  录用日期：2018-2-1，
  
  纸质出版日期：2018-07-25
- 稿件说明：
移动端阅览
赵琳, 王艺鹏, 郝勇. 在轨飞轮故障诊断混合框架设计[J]. 光学精密工程, 2018,26(7):1728-1740.

Lin ZHAO, Yi-peng WANG, Yong HAO. Design of hybrid frame for on-orbit flywheel fault diagnosis[J]. Optics and precision engineering, 2018, 26(7): 1728-1740.
赵琳, 王艺鹏, 郝勇. 在轨飞轮故障诊断混合框架设计[J]. 光学精密工程, 2018,26(7):1728-1740. DOI： 10.3788/OPE.20182607.1728.

Lin ZHAO, Yi-peng WANG, Yong HAO. Design of hybrid frame for on-orbit flywheel fault diagnosis[J]. Optics and precision engineering, 2018, 26(7): 1728-1740. DOI： 10.3788/OPE.20182607.1728.

摘要

为提升飞轮的可靠性，本文对飞轮故障诊断技术进行了研究。通过对基于数学解析模型与基于智能计算的故障诊断方法的对比研究，提出了一种基于神经网络的混合故障诊断方法。该方法首先使用数学解析模型与原系统输出的差值作为一级残差；而后利用该一级残差以及系统可测状态对神经网络进行训练；然后使用混合模型输出的二级残差对系统故障进行检测；最后以飞轮注入母线电压以及电枢电流故障对该方法进行验证：在存在母线电压故障工况下混合模型避免了解析模型电流估计的发散问题，与单神经网络模型相比最大跟踪误差降低了44%。在存在电流故障时，不同的转速工况下与两种单模型相比混合模型的最大跟踪误差降低了90%，跟踪方差减小了10倍以上。混合方法可以有效解决由于解析模型存在建模误差引起的故障诊断不够准确的问题以及由于缺乏训练数据所引起的单神经网络模型不能适应新工况的故障诊断问题。

Abstract

In order to improve flywheel reliability

flywheel fault diagnosis technology was studied. A hybrid fault diagnosis method based on a neural network was proposed

which compares the mathematical analysis model with the flywheel fault diagnosis based on intelligent computing. In this method

the difference between the mathematical model and the original system output was used as the first-order residual. Then

the first-order residual and the system measurements were used to train the neural network. Finally

the second-order residual of the mixed model output was used to detect the system fault. This method was validated using the flywheel injection bus voltage and armature current faults. Under the bus voltage fault working conditions

the hybrid model avoided the divergence problem of current estimation because of the analytical model

which reduced the maximum tracking error by 44% compared with a single neural network model. Under the current fault working conditions

the maximum tracking error of the hybrid model was reduced by 90% and the tracking variance was reduced by more than 10 times under different speed conditions compared with two single neural network models. These results illustrate that the hybrid method can effectively solve the problem of inaccurate fault diagnosis due to the existence of modeling errors in the analytical model

as well as the problem of a single neural network model being unable to adapt to fault diagnosis corresponding to new working conditions because of the lack of training data.

关键词

Keywords

references

韩宇. 执行器故障情况下的航天器姿态容错控制[D]. 哈尔滨: 哈尔滨工业大学, 2016: 2-5. http://www.wanfangdata.com.cn/details/detail.do?_type=degree&id=D01102154

HAN Y. Spacecraft attitude fault-tolerant control methods with actuator fault [D]. Haerbin: Harbin Institute of Technology, 2016: 2-5(in Chinese).

GAO Z, CECATI C, DING S X. A survey of fault diagnosis and fault-tolerant techniques-part 1:Fault diagnosis with model-based and signal-based approaches[J]. IEEE Transactions on Industrial Electronics , 2015, 62(6):3757-3767.

DING S X. Model-based Fault Diagnosis Techniques:Design Schemes, Algorithms, and Tools [M]. Springer Berlin Heidelberg, 2008.

周东华, 叶昊, 王桂增.基于观测器方法的故障诊断技术若干重要问题的探讨[J].自动化学报, 1998, 24(3):338-344.

ZHOU D H, YE H, WANG G Z. Discussion of some important issues of observer based fault diagnosis technique[J]. Acta Automatica Sinica , 1998, 24(3):338-344. (in Chinese)

屠园园, 王大轶, 李文博.基于降维观测器的最优故障诊断算法研究[J].中国空间科学技术, 2017.

TU Y Y, WANG D Y, LI W B.Research on optimal fault diagnosis algorithm based on reduced-order observer[J]. Chinese Space Science and Technology , 2017. (in Chinese)

文传博, 邓露, 吴兰.基于滑模观测器和广义观测器的故障估计方法[J].自动化学报, 2017:1-8.

WEN CH B, DENG L, WU L.Fault Estimation Approaches Based on Sliding Mode Observer and Descriptor Observer[J]. Acta Aeronautica et Astronautica Sinica , 2017:1-8.(in Chinese)

NGUANG S K, ZHANG P, DING S. Parity based fault estimation for nonlinear systems: an LMI approach[C]. American Control Conference. IEEE , 2006: 6.

王征, 高炜欣, 陈义, 等.控制系统中故障检测向量的解耦及次优设计[J].南京理工大学学报, 2017(4):472-478.

WANG ZH, GAO W X, CHEN Y, et al ..Decoupling and sub-optimal design of fault detection vector for control system[J]. Journal of Nanjing University of Science and Technology , 2017(4):472-478(in Chinese)

孙蓉, 刘胜, 张玉芳.基于参数估计的一类非线性系统故障诊断算法[J].控制与决策, 2014, 29(3):506-510.

SUN R, LIU SH, ZHANG Y F.Fault diagnosis algorithm of a class of nonlinear system based on parameter estimation[J]. Control and Decision , 2014, 29(3):506-510. (in Chinese)

王君, 姚晓婉, 李炜. NNCS混合容错控制方法[J].控制与决策, 2017, 1-13.

WANG J, YAO X W, LI W.Hybrid fault-tolerant control method research of NNCS[J]. Control and Decision , 2017:1-13. (in Chinese)

李业波, 李秋红, 王健康.基于ImOS-ELM的航空发动机传感器故障自适应诊断技术[J].航空学报, 2013, 34(10):2316-2324.

LI Y B, LI Q H, WANG J K. Sensor fault adaptive diagnosis of aero-engines based on ImOS-ELM[J]. Acta Aeronautica et Astronautica Sinica , 2013, 34(10):2316-2324(in Chinese)

鲁峰, 黄金泉, 吕怡秋.基于非线性自适应滤波的发动机气路部件健康诊断方法[J].航空学报, 2013, 34(11):2529-2538.

LU F, HUANG J Q, LV Y Q. Design and simulation Validation of an integrated on-board Aircraft engine diagnostic architecture[J]. Acta Aeronautica et Astronautica Sinica , 2013, 34(11):2529-2538. (in Chinese).

GAO Z, CECATI C, DING S X. A Survey of Fault Diagnosis and Fault-Tolerant Techniques-Part Ⅱ:Fault Diagnosis With Knowledge-Based and Hybrid/Active Approaches[J]. IEEE Transactions on Industrial Electronics , 2015, 62(6):3768-3774.

PATTON R J, LOPEZ-TORIBIO C J, UPPAL F J. Artificial Intelligence approaches to fault diagnosis for dynamic systems[J]. International Journal of Applied Mathematics & Computer Science , 1999, 9(3):471-518.

陈子琴, 高向东, 王琳.大功率盘形激光焊焊缝背面宽度预测[J].光学精密工程, 2017, 25(9):2524-2531.

CHEN Z Q, GAO X D, WANG L. Weld width prediction of weldment bottom surface in high-power disk laser welding[J]. Opt. Precision Eng ., 2017, 25(9):2524-2531. (in Chinese)

叶建华, 高诚辉, 江吉彬.五轴机床旋转轴误差的在机测量与模糊径向基神经网络建模[J].光学精密工程, 2016, 24(4):826-834.

YE J H, GAO CH H, JIANG J B. On-machine measurement and fuzzy RBF neural network modeling for geometric errors of rotary axes of five-axis machine tools[J]. Opt. Precision Eng ., 2016, 24(4):826-834. (in Chinese)

张恩忠, 赵继, 冀世军, 等.精密加工实验台热误差建模与补偿方法的对比分析[J].光学精密工程, 2016, 24(10s):520-526.

ZHANG E ZH, ZHAO J, JI SH J, et al ..Comparative analysis on thermal error modeling and compensation method of precision matching test brch[J]. Opt. Precision Eng ., 2016, 24(10s):520-526. (in Chinese)

秦国华, 谢文斌, 王华敏.基于神经网络与遗传算法的刀具磨损检测与控制[J].光学精密工程, 2015, 23(5):1314-1321.

QIN G H, XIE W B, WANG H M. Detection and control for tool wear based on neural network and genetic algorithm[J]. Opt. Precision Eng ., 2015, 23(5):1314-1321. (in Chinese)

葛哲学, 杨拥民, 胡政.一种新颖的直升机舵回路故障诊断方法[J].航空学报, 2006, 27(6):1122-1126.

GE ZH X, YANG Y M, HU ZH. A new fault diagnosis method of helicopter actuator loop[J]. Acta Aeronautica et Astronautica Sinica , 2006, 27(6):1122-1126. (in Chinese)

龚学兵, 王日新, 徐敏强.基于数据关联性分析的飞轮异常检测[J].航空学报, 2015, 36(3):898-906.

GONG X B, WANG R X, XU M Q. Abnormality detection for flywheels based on data association analysis[J]. Acta Aeronautica et Astronautica Sinica , 2015, 36(3):898-906.. (in Chinese)

SOBHANI-TEHRANI E, TALEBI H A, KHALASTCHI K. Hybrid fault diagnosis of nonlinear systems using neural parameter estimators[J]. Neural Networks the Official Journal of the International Neural Network Society , 2014, 50(2):12.

KHALASTCHI E, KALECH M, ROKACH L. A hybrid approach for improving unsupervised fault detection for robotic systems[J]. Expert Systems with Applications , 2017, 81:372-383.

BIALKE B. High fidelity mathematical modeling of reaction wheel performance[J]. Advances in the Astronautical Sciences , 1998, 98:483-496.

HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators [M]. Elsevier Science Ltd., 1989.

浏览量

452

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于信息融合的机器人薄壁轴承故障智能诊断

基于神经网络的全斯托克斯光电探测器

基于圆卷积神经网络的粘连导电粒子检测

面向领域自适应的部分最优传输高光谱图像分类

基于热传导和卷积神经网络的磨床主轴热误差预测