基于综合应力工作态试验和神经网络的CMG失效边界域预测

doi:10.7527/S1000-6893.2020.24208

固体力学与飞行器总体设计

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于综合应力工作态试验和神经网络的CMG失效边界域预测

黄首清^1,2, 刘守文^1,2, 翟百臣³, 周原^1,2, 黄小凯^1,2, 秦泰春^1,2

1. 航天机电产品环境可靠性试验技术北京市重点实验室, 北京 100094;
2. 北京卫星环境工程研究所, 北京 100094;
3. 北京控制工程研究所, 北京 100190

收稿日期:2020-05-11 修回日期:2020-06-16 发布日期:2020-07-10
通讯作者: 周原 E-mail:174478656@qq.com
基金资助:
国防科工局民用航天技术预先研究项目（A0201）；中国人民解放军装备发展部装备预先研究项目（41402010103）

Prediction of CMG failure boundary domain based on combined stress test and neural network

HUANG Shouqing^1,2, LIU Shouwen^1,2, ZHAI Baichen³, ZHOU Yuan^1,2, HUANG Xiaokai^1,2, QIN Taichun^1,2

1. Beijing Key Laboratory of Environment & Reliability Test Technology for Aerospace Mechanical & Electrical Products, Beijing 100094, China;
2. Beijing Institute of Spacecraft Environment Engineering, Beijing 100094, China;
3. Beijing Institute of Control Engineering, Beijing 100190, China

Received:2020-05-11 Revised:2020-06-16 Published:2020-07-10
Supported by:
Civil Aerospace Technology Research Project from State Administration of Science, Technology and Industry for National Defense(A0201); Equipment Research Project of PLA Equipment Development Department (41402010103)

摘要/Abstract

摘要： 本文设计了一种可同时模拟真空热环境和CMG与航天器角动量交换工况的试验设备，提出了模拟在轨真空环境下温度、CMG框架转速、航天器转速3种应力的工作态试验方法，给出了适用于神经网络的CMG运行状态定量表达方法，利用少量试验数据和神经网络方法对工作极限转速矩阵、失效边界、失效边界域进行预测，分析了经验样本对预测结果的影响，以及各应力对其他应力工作域的耦合影响，并给出了预测结果的可信度分析方法。研究结果表明，所提出的方法可以更真实模拟CMG在轨工作状态的同时显著节省试验经费和时间，并具有较高的预测准确性和多应力工作场景适应性，对I和Ⅱ两类训练数据集分别获得100%和98.8%的预测正确率，给出了仅凭试验数据无法得到的55℃下的转速失效边界，并且可以内化试验数据背后的工程经验。

关键词: 控制力矩陀螺, 工作态试验, 神经网络, 失效边界域, 综合应力

Abstract: This study designs the test equipment for simultaneous simulation of the vacuum thermal environment and angular momentum exchange conditions between a CMG (Control Moment Gyroscope) and a spacecraft, and proposes a combined stress working-state test method to simulate the in orbit vacuum temperature, CMG gimbal rotational speed and spacecraft rotational speed. A quantitative expression method for CMG running status suitable for a neural network model is applied. Based on relatively little amount of test results, the neural network model after training is used to predict the working limit rotational speed matrix, the failure boundary and the failure boundary domain. Furthermore, the influence of experience samples on the prediction results is analyzed, and the coupling effect of each stress on the working domain of other stresses investigated, and the predicted initial value by the neural network proposed to reflect the reliability of the prediction results. The results show that the presented method can not only simulate the real working-state better but also significantly save both test cost and time, in addition to high prediction accuracy and good adaptability under multi-stress working conditions. The prediction accuracy can reach up to 100% and 98.8% based on the two training data sets I and Ⅱ, respectively. The failure boundary of rotational speeds at 55 ℃ is given which cannot be obtained only via the test data, and the engineering experience behind the test data can be internalized.

Key words: control moment gyroscopes, working-state tests, neural networks, failure boundary domains, combined stress

中图分类号:

V416

黄首清, 刘守文, 翟百臣, 周原, 黄小凯, 秦泰春. 基于综合应力工作态试验和神经网络的CMG失效边界域预测[J]. 航空学报, 2021, 42(4): 524208-524208.

HUANG Shouqing, LIU Shouwen, ZHAI Baichen, ZHOU Yuan, HUANG Xiaokai, QIN Taichun. Prediction of CMG failure boundary domain based on combined stress test and neural network[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 524208-524208.

参考文献

[1] LAPPAS V J, STEYN W H, UNDERWOOD C I. Torque amplification of control moment gyros[J]. Electronics Letters, 2002, 38(15):837-839.
[2] TANIWAKI S, OHKAMI Y. Precision attitude control of spacecraft with control moment gyros[C]//AIAA Guidance, Navigation, and Control Conference and Exhibit. Reston:AIAA, 2006.
[3] Marshall Space Flight Center. The Proceedings of the committee to investigate the SKYLAB CMG No.2 orbital anomalies:NASA-N79-76857[R]. Washington, D.C.:NASA, 1974.
[4] GURRISI C, SEIDEL R, DICKERSON S, et al. Space station control moment gyroscope lessons learned:NASA-CP-2010-216272[R]. Washington,D.C.:NASA, 2010.
[5] 王正青. 面向实战摸清底数——谈复杂环境与边界条件下的武器装备试验鉴定[J]. 现代防御技术, 2019, 47(5):1-7. WANG Z Q. Combat oriented base performance testing:testing identification of weapon system in complex scenes and boundary conditions[J]. Modern Defence Technology, 2019, 47(5):1-7(in Chinese).
[6] 李阿楠, 廖学军. 我军开展武器装备作战试验鉴定的思考[J]. 装备学院学报, 2016, 27(1):107-110. LI A N, LIAO X J. Reflection on appraisal on PLA'S weapons and equipments operational test[J]. Journal of Equipment Academy, 2016, 27(1):107-110(in Chinese).
[7] 赵继广, 柯宏发, 康丽华, 等. 武器装备作战试验发展与研究现状分析[J]. 装备学院学报, 2015, 26(4):113-119. ZHANG J G, KE H F, KANG L H, et al. Development and current researches of weapon equipment operational test[J]. Journal of Equipment Academy, 2015, 26(4):113-119(in Chinese).
[8] 宋燕. 基于失效边界域的耐久性渐变退化分析与仿真研究[D]. 北京:北京航空航天大学, 2014. SONG Y. The analysis and simulation of durability gradient degradation based on fuzzy failure domain[D]. Beijing:Beihang University, 2014(in Chinese).
[9] 徐子健, 南宫自军, 李炳蔚, 等. 电磁继电器冲击失效边界研究[J]. 兵器装备工程学报, 2020,41(9):51-57,74. XU Z J, NANGONG Z J, LI B W, et al. Research on failure boundary of electromagnetic relay[J]. Journal of Ordnance Equipment Engineering, 2020,41(9):51-57,74(in Chinese).
[10] United States Air Force. Design, construction, and testing requirements for one of a kind space equipment:DOD-HDBK-343[S]. Washington, D.C.:United States Air Force, 1986.
[11] Department of Defense of United States. Director, operational test and evaluation FY 2017 annual report[R]. Washington, D.C.:Department of Defense of United States, 2017.
[12] Department of Defense of United States. Director, operational test and evaluation FY 2018 annual report[R]. Washington, D.C.:Department of Defense of United States, 2018.
[13] Department of Defense of United States. Director, operational test and evaluation FY 2019 annual report[R]. Washington,D.C.:Department of Defense of United States, 2019.
[14] 姚泽民,黄首清,刘大志, 等. 热-声-振耦合效应对薄壁叶片结构应变影响的试验研究[J]. 航天器环境工程, 2019, 36(4):363-368. YAO Z M, HUANG S Q, LIU D Z, et al. Experimental study of the effect of thermal-acoustics-vibration coupling on the strain of thin-blade structure[J]. Spacecraft Environment Engineering, 2019, 36(4):363-368(in Chinese).
[15] 虎刚, 徐映霞, 吴金涛. 200 Nms单框架控制力矩陀螺的热平衡试验[J]. 空间控制技术与应用, 2008, 34(1):27-30. HU G, XU Y X, WU J T. Thermal balance test on a 200 Nms single-gimbal CMG[J]. Aerospace Control and Application, 2008, 34(1):27-30(in Chinese).
[16] 魏大忠, 李刚, 伏蓉, 等. 天宫一号单框架控制力矩陀螺研制及长寿命转子轴系技术[J]. 中国科学:技术科学, 2014, 44(3):261-268. WEI D Z, LI G, FU R, et al. Design of SGCMG and long life rotor bearing system technology in Tiangong-1[J]. Scientia Sinica Technologica, 2014, 44(3):261-268(in Chinese).
[17] LIU S W, HUANG S Q, LU L, et al. Thermal vacuum and swivel table tests of a CMG and fault mechanism analysis[J]. Journal of Aerospace Engineering, 2018, 31(5):04018069-1-12.
[18] 王雅梦. 控制力矩陀螺轴承组件温度场分析[D]. 洛阳:河南科技大学, 2015:35-59. WANG Y M. Analysis of temperature field of bearing assembly for control moment gyroscope[D]. Luoyang:Henan University of Science and Technology, 2015:35-59(in Chinese).
[19] 张俊红,张桂昌,何振鹏, 等. 基于正交实验和神经网络的轴系主轴承润滑特性优化[J]. 内燃机学报, 2011, 29(5):461-467. ZHANG J H, ZHANG G C, HE Z P, et al. Optimization of crankshaft-bearing lubricating characteristics based on orthogonal experiment and neural network[J]. Transactions of CSICE, 2011, 29(5):461-467(in Chinese).
[20] 单钧麟, 汪立新, 秦伟伟, 等. 控制力矩陀螺自平衡车粒子群优化LQR控制[J]. 兵器装备工程学报, 2019, 40(12):100-104. DAN J L, WANG L X, QIN W W, et al. Particle swarm optimization LQR control of self-balancing vehicles with control moment gyro[J]. Journal of Ordnance Equipment Engineering, 2019, 40(12):100-104(in Chinese).
[21] MACKUNIS W, LEVE F, PATRE P, et al. Adaptive neural network-based satellite attitude control in the presence of CMG uncertainty[J]. Aerospace Science and Technology, 2016, 54(7):218-228.
[22] 李海涛, 林杰, 韩邦成. 基于ESO的DGVSCMG双框架伺服系统不匹配扰动抑制[J]. 航空学报, 2018, 39(4):421641. LI H T, LIN J, HAN B C. Mismatched disturbance rejection of double gimbal servo system in variable speed control moment gyroscope using a novel ESO method[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(4):421641(in Chinese).
[23] 飞思科技产品研发中心. 神经网络理论与MATLAB 7实现[M]. 北京:电子工业出版社, 2005:100-105. FECIT Technological Product Research Center. Neural network theory and implementation of MATLAB 7[M]. Beijing:Publishing House of Electronics Industry, 2005:100-105(in Chinese).

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于综合应力工作态试验和神经网络的CMG失效边界域预测

Prediction of CMG failure boundary domain based on combined stress test and neural network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	马菲, 张琼, 赖培军, 岳一笛. 基于BP神经网络的试飞训练安全性量化模型[J]. 航空学报, 2024, 45(5): 529957-529957.
[2]	倪育德, 闫苗玉, 刘瑞华. 基于DOA-BP神经网络的电离层TEC短期预测[J]. 航空学报, 2024, 45(4): 328707-328707.
[3]	李忠智, 马金毅, 艾剑良, 董一群. 拟VGG16网络的航空传感器故障检测分类[J]. 航空学报, 2023, 44(S1): 727615-727615.
[4]	刘武, 吴云燕, 刘玮, 田明明, 黄天鹏. 考虑未知扰动的RLV再入鲁棒容错姿态控制[J]. 航空学报, 2023, 44(S1): 727787-727787.
[5]	刘晨阳, 吴大伟, 郭一泽, 吕欣赛, 周佳妮, 邵书义. 不确定强耦合下四旋翼姿态鲁棒自适应控制[J]. 航空学报, 2023, 44(S1): 727645-727645.
[6]	王志凯, 陈盛, 范玮. 神经网络宽度对燃烧室排放预测的影响[J]. 航空学报, 2023, 44(5): 126816-126816.
[7]	何磊, 钱炜祺, 董康生, 易贤, 柴聪聪. 基于卷积神经网络的结冰翼型气动特性建模[J]. 航空学报, 2023, 44(5): 126434-126434.
[8]	王宏伦, 王延祥, 刘一恒. 基于轨迹映射的无人机拖曳式空中回收轨迹优化[J]. 航空学报, 2023, 44(20): 628775-628775.
[9]	朱祥维, 沈丹, 肖凯, 马岳鑫, 廖祥, 古富强, 余芳文, 高柯夫, 刘经南. 类脑导航的机理、算法、实现与展望[J]. 航空学报, 2023, 44(19): 28569-028569.
[10]	岳承磊, 汪雪川, 岳晓奎, 宋婷. 基于逆强化学习的航天器交会对接方法[J]. 航空学报, 2023, 44(19): 328420-328420.
[11]	李怀璐, 王旭, 王霄, 赵彤, 张伟伟. 大迎角机动飞行的气动力建模与飞行仿真[J]. 航空学报, 2023, 44(19): 128410-128410.
[12]	梁益铭, 李广宁, 徐敏. 基于机器学习的智能控制数值虚拟飞行方法[J]. 航空学报, 2023, 44(17): 128098-81280986.
[13]	宋玉存, 葛泉波, 朱军龙, 陆振宇. 基于梯度差自适应学习率优化的改进YOLOX目标检测算法[J]. 航空学报, 2023, 44(14): 327951-327951.
[14]	任乐亮, 鲜勇, 李少朋, 雷刚, 伍薇, 李冰. 基于改进二阶优化器并行学习的弹道导弹神经网络落点预测方法[J]. 航空学报, 2023, 44(14): 327964-327964.
[15]	董磊, 陈泓兵, 陈曦, 赵长啸. 基于DQN的单一飞行员驾驶模式分布式多智能体联盟任务分配策略[J]. 航空学报, 2023, 44(13): 327895-327895.