Health Evaluation of Missile Control System based on RBF and SOM

doi:10.12382/bgxb.2021.0219

Abstract

Abstract: Traditional health evaluation methods of missile weapon rely heavily on the experience and ability of designers and product experts，which is inefficient and inaccurate.For missile control system，a health state evaluation method based on Radial Basis Function（RBF） network observer and Self-organizing map（SOM）network is proposed. The adaptive fault observer based on RBF network is used to calculate the residuals of output signals and the adaptive discriminant thresholds under different working conditions. Through the comparison between the residual and threshold values，the fault detection is realized.The health evaluation model based on SOM network is used to realize the cluster analysis of residuals. Through the distance measurement，the health evaluation is realized.A missile control system case is used to verify that the proposed method can detect 10 different fault modes and evaluate 10 different health states accurately, and provides technical support for maintenance support and logistics management.

Key words: missilecontrolsystem, healthevaluation, radialbasisfunctionneuralnetwork, self-organizingmappingnetworks, adaptivethreshold

CLC Number:

TJ01
E919

LIU Yue, LIU Tielin, JIANG Xiangzheng, HAN Yueming. Health Evaluation of Missile Control System based on RBF and SOM[J]. Acta Armamentarii, 2022, 43(4): 931-939.

References

［1］杨立峰，王亮，冯佳晨.基于PHM技术的导弹维修保障[J].海军航空工程学院学报，2010，25(4): 447-450.
YANG L F，WANG L，FENG J C.Missile maintenance support based on PHM technology[J].Journal of Naval Aeronautical Engineering Institute，2010，25(4): 447-450. (in Chinese)
[2］胡冬，谢劲松，吕卫民.故障预测与健康管理技术在导弹武器系统中的应用[J].导弹与航天运载技术， 2010(4):24-30．
HU D，XIE J S，L W M. Application of fault prediction and health management technology in missile weapon system[J].Missile and Space Launch Technology，2010(4): 24-30. (in Chinese)
[3］张泽奇，刘晓芳，陈曦.基于PHM 的导弹状态管理研究[J].信息技术，2010(7): 107-109．
ZHANG Z Q，LIU X F，CHEN X.Research on missile state management based on PHM[J].Information Technology，2010(7):107-109. (in Chinese)
[4］徐利明，史文森，陈建华. 基于PHM的弹道导弹装备健康管理系统设计[C]∥航空工业测控技术发展中心、中国航空学会测试技术分会、状态监测特种传感技术航空科技重点实验室.第十六届中国航空测控技术年会论文集，北京：测控技术杂志社，2019:98-101.
XU L M，SHI W S，CHEN J H.Design of the health management system of ballistic missile equipment based on PHM[C]∥Proceedings of Measurement and Control Technology Development Center of Aviation Industry，Test Technology Branch of Chinese Society of Aviation，Key Laboratory of Aviation Science and Technology of Special Sensor Technology for Condition Monitoring. Proceedings of the 16th Annual Conference of China Aviation Measurement and Control Technology，Beijing：Journal of Measurement and Control Technology，2019: 98-101 (in Chinese)
[5］赵建忠，叶文，张磊.基于数据融合和改进新陈代谢不等间距GM(1，1)模型的导弹装备故障预测[J].兵工学报，2014，35(10): 1689-1695.
ZHAO J Z，YE W，ZHANG L.Missile equipment failure prediction based on data fusion and improved metabolic unequal spacing GM(1，1) model[J].Journal of Military Engineering，2014，35(10): 1689-1695. (in Chinese)
[6］刘琦，李耀芳，彭慧卿，等电子系统故障预测方法综述[J].天津城市建设学院学报，2016，22(4):298-301，306.
LIU Q， LI Y F，PENG H Q，et al. Overview of electronic system fault prediction methods[J]. Journal of Tianjin Institute of Urban Construction，2016，22(4): 298-301，306. (in Chinese)
[7］薛东风，叶继坤.于HMM的电子设备健康状态评估方法[J].现代防御技术，2013，41(2):187-191.
XUE D F，YE J K.Evaluation method of electronic equipment health status based on HMM[J].Modern Defense Technology，2013，41(2):187-191. (in Chinese)
[8］ SUN Q，ZHOU Y，LI M.Bearing operating state evaluation based on improved HMM[J]. International Journal of Pattern Recognition and Artificial Intelligence，2020，34(6): 2059016.
[9］豆金昌.锂离子电池健康评估及剩余使用寿命预测方法研究[D].南京：南京航空航天大学，2013.
DOU J C.Research on lithium-ion battery health assessment and remaining service life predictionmethod[D].Nanjing：Nanjing University of Aeronautics and Astronautics，2013. (in Chinese)
[10］ XING J，ZENG Z，ZIO E. A framework for dynamic risk assessment with condition monitoring data and inspection data[J]. Reliability Engineering & System Safety，2019，191:106552.
[11］张任，胥芳，陈教料，等.基于PSO-RBF神经网络的锂离子电池健康状态预测[J].中国机械工程，2016， 27(21): 2975-2981.
ZHANG R，XU F，CHEN J L，et al. Prediction of health status of lithium-ion battery based on PSO-RBF neural network[J].China Mechanical Engineering，2016，27(21): 2975-2981. (in Chinese)
[12］陈峥，顾青峰，沈世全，等. 基于健康特征提取和PSO-RBF神经网络的锂离子电池健康状态预测[J]. 昆明理工大学学报(自然科学版)，2020，45(6):92-103.
CHEN Z，GU Q F，SHEN S Q，et al. Health state prediction of lithium-ion battery based on health feature extraction and PSO-RBF neural network[J].Journal of Kunming University of Science and Technology (Natural Science Edition)，2020，45(6): 92-103. (in Chinese)
[13］曹惠玲，黄乐腾，李志伟，等.基于SOM神经网络的航空发动机滑油系统健康评估[J].中国民航大学学报，2014，32(6): 19-22.
CAO H L，HUANG L T，LI Z W，et al. Aeroengine lubricating oil system health assessment based on SOM neural network[J]. Journal of Civil Aviation University of China，2014，32(6):19-22. (in Chinese)
[14］方博.滚动轴承健康状态评估方法研究[D].哈尔滨：哈尔滨工业大学，2019.
FANG B. Research on rolling bearing health condition assessment method[D].Harbin：Harbin Institute of Technology，2019. (in Chinese)
[15］彭宇，刘大同.数据驱动故障预测和健康管理综述[J]. 仪器仪表学报，2014，35(3): 481-495.
PENG Y，LIU D T.Summary of data-driven failure prediction and health management[J].Chinese Journal of Scientific Instrument，2014，35(3): 481-495. (in Chinese)
[16］ SING H J，DARPE A K，SINGH S P. Bearing remaining useful life estimation using an adaptive data-driven model based on health state change point identification and K-means clustering[J].Measurement Science and Technology，2020，31(8):085601.
[17］宋玉琴，章卫国，刘小雄.基于RBF神经网络观测器飞控系统故障诊断[J].计算机仿真，2010，27(3): 85-88，93.
SONG Y Q，ZHANG W G，LIU X X. Fault diagnosis of flight control system based on RBF neural network observer [J]. Computer Simulation，2010，27(3):85-88，93.(in Chinese)
[18］刘芳. 基于SOM聚类的可视化方法及应用研究[J]. 计算机应用研究，2012，29(4):1300-1303.
LIU F. Research on visualization method and application based on SOM clustering[J].Application Research of Computers，2012，29(4):1300-1303. (in Chinese)

[1]	HUANG Shaling， ZHU Hongzhi， CHENG Xiangli， XIE Yubin. Adaptive Threshold Setting Method for Layer-count in Penetration Fuse [J]. Acta Armamentarii, 2020, 41(9): 1762-1771.
[2]	WANG Cheng， WU Yan， YANG Tingfei. Improving the Detection Accuracy of Wake Targets by Improved One-class Support Vector Machine [J]. Acta Armamentarii, 2020, 41(9): 1887-1893.
[3]	LI Bin, PANG Yong-jie, ZHU Xiao-meng, CHENG Yan-xue. 6σ Optimization Design of Ring-stiffened Composite Pressure Hull of Underwater Vehicle [J]. Acta Armamentarii, 2018, 39(6): 1171-1177.