基于改进PCA的导弹装备健康表征参数提取方法

doi:10.12305/j.issn.1001-506X.2022.10.34

摘要/Abstract

摘要：

针对导弹装备健康状态信息复杂且相互交融、健康表征参数难以提取的问题, 提出一种基于改进主成分分析(principal component analysis, PCA)的装备健康状态低维敏感表征参数的确定方法。该方法先开展装备扩展故障模式及影响分析, 构建初始高维特征参数集, 再利用改进PCA对参数集进行降维处理, 在最大化高维表征参数全局特征方差的目标下, 提取出非线性表征参数子集。将该方法应用到导弹舵机健康评估实验中, 使用故障注入模拟设备进行验证。结果表明, 采用所提方法提取的健康表征参数对舵机健康状态识别准确率高, 说明所提方法在提取导弹装备健康表征参数中具有明显的优越性。

关键词: 导弹装备, 健康管理, 表征参数, 改进主成分分析, 舵机

Abstract:

Aiming at the problems of complex and integrated missile equipment health status information and difficult to extract health characterization parameters, a method for determining low-dimensional sensitive characterization parameters of equipment health status based on improved principal component analysis (PCA) is proposed. Firstly, the equipment extensional failure mode and effect analysis are carried out to construct the initial high-dimensional characteristic parameter set. Then, the improved PCA is used to reduce the dimension of the parameter set. Under the goal of maximizing the global characteristic variance of the high-dimensional characterization parameters, the nonlinear characterization parameters subset is extracted. The proposed method is applied to the health evaluation experiment of missile steering gear, and verified by the fault injection simulation equipment. The results show that the health characterization parameters extracted by the proposed method have high recognition accuracy for the health status of steering gear, indicating that the proposed method has obvious advantages in the extraction of missile equipment health characterization parameters.

Key words: missile equipment, health management, characterization parameter, improved principal component analysis (PCA), steering gear

中图分类号:

E917

郭璐, 刘晓东, 魏东涛, 朱璞. 基于改进PCA的导弹装备健康表征参数提取方法[J]. 系统工程与电子技术, 2022, 44(10): 3275-3281.

Lu GUO, Xiaodong LIU, Dongtao WEI, Pu ZHU. Extraction method of missile equipment health characterization parameters based on improved PCA[J]. Systems Engineering and Electronics, 2022, 44(10): 3275-3281.

图/表 13

图1

表1

舵机aFMEA"

产品	功能	故障模式	故障原因	故障机理	故障影响	故障发生工况	环境应力	故障检测方式	故障关联参数	参数变化
电机插头	接通直流电源	断路	接触不良, 插头氧化	处于自然环境中贮存导致电机插头氧化	舵机舵面不能摆动	贮存	温度、湿度	电流表	温度、湿度、电流、电压	无电流输入
电机	驱动双联泵	转速下降	换向器与电刷间接触不良	电机频繁换向造成换向器与电刷间磨损	舵机响应迟缓	贮存	温度、振动	测速仪	电机转速、电流	电机转速下降、输入电流增大
双联泵	提供液压能源	动密封渗油	密封环磨损	输出轴高速运动发热造成密封圈磨损	舵机响应迟缓、舵面运行不平稳、舵机功率增大	飞行	温度	无	温度、轴转速	系统温度升高、轴转速增大
过滤器	保证工作油液清洁	严重堵塞	油液污染、过滤面积小	液压回路中各摩擦部件相对运动形成磨损颗粒、补油过程中带入系统的颗粒物堵塞过滤器	舵机功率增大、舵面不能正常摆动	贮存、飞行	温度	油液清洁度检测	油液清洁度	油液颗粒度增大
控制插头	提供控制信号	断路	电位计输入信号引脚接触不良	处于自然环境中贮存, 插头氧化, 舵机处于开环控制	舵面处于最大和最下角之间来回摆动	贮存	温度、湿度	无	温度、湿度、电流	电位器无电流输出
伺服阀	控制和功率放大	不能换向	阀芯卡死, 油液污染	液压回路中各摩擦部件相对运动形成磨损, 颗粒物污染油液造成阀芯卡死	舵面不能摆动	贮存、飞行	温度	流量计	油液清洁度、流量	油液颗粒度较大、回路中流量为零
反馈电位器	将连杆位移转换为电信号	输出精度差	电位器有磨损或损坏	电位器电刷往复运动造成电刷磨损电阻增大	舵机运动精度下降	飞行	温度、振动	测量电阻	电阻	电位器阻值增大
┇
低压安全阀	限制油箱压力过高	降压开启	弹簧刚度下降	弹簧老化弹性系数下降造成堵头承载压力下降	舵面运行不稳	贮存	温度、振动	压力表	时间、压力	油箱压力长时间达不到额定值

表1

表2

表3

图2

图3

表4

图4

表5

表6

图5

图6

表7

参考文献 21

1	李向前. 复杂装备故障预测与健康管理关键技术研究[D]. 北京: 北京理工大学, 2014.
	LI X Q. Research on key technologies of complex equipment fault prediction and health management[D]. Beijing: Beijing Institute of Technology, 2014.
2	赵志傲. 装备PHM系统故障预测能力验证技术[D]. 长沙: 国防科技大学, 2018.
	ZHAO Z A. Verification technology of fault prediction ability of equipped PHM system[D]. Changsha: National University of Defense Technology, 2018.
3	RAHMAN M M , UDDIN M N . Online unbalanced rotor fault detection of an IM drive based on both time and frequency domain analyses[J]. IEEE Trans.on Industry Applications, 2017, 53 (4): 4087- 4096. doi: 10.1109/TIA.2017.2691736
4	ESTIMA J O , MARQUES C A J . A new algorithm for real-time multiple open-circuit fault diagnosis in voltage-fed PWM motor drives by the reference current errors[J]. IEEE Trans.on Industrial Electronics, 2013, 60 (8): 3496- 3505. doi: 10.1109/TIE.2012.2188877
5	NIE S S , PEI X J , CHEN Y , et al. Fault diagnosis of PWM DC-DC converters based on magnetic component voltages equation[J]. IEEE Trans.on Power Electronics, 2014, 29 (9): 4978- 4988. doi: 10.1109/TPEL.2013.2283881
6	BHARDWAJ M , CHOUDHURY S , POLEY R , et al. Online frequency response analysis: a powerful plug-in tool for compensation design and health assessment of digitally controlled power converters[J]. IEEE Trans.on Industry Applications, 2016, 52 (3): 2426- 2435. doi: 10.1109/TIA.2016.2522951
7	PARK J K , HUR J . Detection of inter-turn and dynamic eccentricity faults using stator current frequency pattern in IPM-type BLDC motors[J]. IEEE Trans.on Industrial Electronics, 2016, 63 (3): 1771- 1780. doi: 10.1109/TIE.2015.2499162
8	BOUZIDA A , TOUHAMI O , IBTIOUEN R , et al. Fault diagnosis in industrial induction machines through discrete wavelet transform[J]. IEEE Trans.on Industrial Electronics, 2011, 58 (9): 4385- 4395. doi: 10.1109/TIE.2010.2095391
9	TRACHI Y , ELBOUCHIKHI E , CHOQUEUS V , et al. Induction machines fault detection based on subspace spectral esti mation[J]. IEEE Trans.on Industrial Electronics, 2016, 63 (9): 5641- 5651. doi: 10.1109/TIE.2016.2570741
10	YIN S , DING S X , XIE X , et al. A review on basic data-driven approaches for industrial process monitoring[J]. IEEE Trans.on Industrial Electronics, 2014, 61 (11): 6418- 6428. doi: 10.1109/TIE.2014.2301773
11	MOHAGHEGHI S , HARLEY R G , HABETLER T G , et al. Condition monitoring of power electronic circuits using artificial neural networks[J]. IEEE Trans.on Power Electronics, 2009, 24 (10): 2363- 2367. doi: 10.1109/TPEL.2009.2017806
12	GAO Z , DING S X , CECATI C . Real-time fault diagnosis and fault-tolerant control[J]. IEEE Trans.on Industrial Electronics, 2015, 62 (6): 3752- 3756. doi: 10.1109/TIE.2015.2417511
13	BOUAZIZ M F , ZAMAI E , DUVIVIER F . Towards Bayesian network methodology for predicting the equipment health factor of complex semiconductor systems[J]. International Journal of Production Research, 2013, 51 (15): 4597- 4617. doi: 10.1080/00207543.2013.775525
14	JAHROMI A , PIERCY R , CRESS S , et al. An approach to power transformer asset management using health index[J]. IEEE Electrical Insulation Magazine, 2009, 25 (2): 20- 34. doi: 10.1109/MEI.2009.4802595
15	ZHANG L L , QIAO F , WANG J K , et al. Equipment health assessment based on improved incremental sup an approach to power transformer asset management using health index port vector data description[J]. IEEE Trans.on Systems, Man, and Cybernetics: Systems, 2021, 51 (5): 3205- 3216. doi: 10.1109/TSMC.2019.2919468
16	WANG L , TANG X A , ZHANG J D , et al. Correlation analysis for exploring multivariate data sets[J]. IEEE Access, 2018, 6, 44235- 44243. doi: 10.1109/ACCESS.2018.2864685
17	TAO K , ZHENG W , JIANG D C . Entropy method for structural health monitoring based on statistical cause and effect analysis of acoustic emission and vibration signals[J]. IEEE Access, 2019, 7, 172515- 172525. doi: 10.1109/ACCESS.2019.2956289
18	XIONG H , SHANG P J . Weighted multifractal cross-correlation analysis based on Shannon entropy[J]. Communications in Nonlinear Science and Numerical Simulation, 2016, 30 (1-3): 268- 283. doi: 10.1016/j.cnsns.2015.06.029
19	YU Y , MA G H , HAO Z L , et al. Correlation analysis for screening key parameters for passive system reliability analysis[J]. Annals of Nuclear Energy, 2015, 77 (C): 23- 29.
20	PANDOVE D , GOEL S , RANI R . General correlation coefficient based agglomerative clustering[J]. Cluster Computing, 2019, 22 (2): 553- 583. doi: 10.1007/s10586-018-2863-y
21	SHIN Y , PARK C . Analysis of correlation based dimension reduction methods[J]. International Journal of Applied Mathematics and Computer Science, 2011, 21 (3): 549- 558. doi: 10.2478/v10006-011-0043-9

X	表征参数
X₁	轴转速
X₂	回路压力
X₃	输入电流
X₄	作动筒速度
X₅	回路流量
X₆	电机转速
X₇	输出电流
X₈	泵油量
X₉	油液颗粒度
X₁₀	系统温度
X₁₁	油箱压力
X₁₂	电阻
X₁₃	系统湿度

表征参数	特征值	贡献率/%	累计贡献率/%
X₁	6.241	48.011	48.011
X₂	3.087	23.748	71.759
X₃	1.395	10.732	82.491
X₄	0.724	5.570	88.061
X₅	0.674	5.185	93.246
X₆	0.406	3.123	96.369
X₇	0.215	1.654	98.023
X₈	0.139	1.069	99.092
X₉	0.118	0.908	100
X₁₀	2.37 E-12	1.82 E-3	100
X₁₁	5.28 E-14	4.06 E-15	100
X₁₂	1.64 E-14	1.26 E-15	100
X₁₃	1.02 E-15	7.85 E-17	100

特征参数	M₁	M₂	M₃	M₄
X₁	0.874	0.720	-0.162	0.563
X₂	0.586	0.935	-0. 756	0.438
X₃	0.413	-0.369	0.427	0.519
X₄	0.741	0.904	-2.431E-02	0.917
X₅	0.925	0.813	-0.168	0.140
X₆	-0.353	0.126	0.430	-0.607
X₇	-0.272	0.123	3.758E-02	0.916
X₈	-0.157	-0.642	3.150E-02	0.822
X₉	-0.384	0.987	8.262E-02	0.155
X₁₀	0.662	0.841	-4.31E-02	0.137
X₁₁	-0.186	0.605	-0.179	0.342
X₁₂	0.415	0.726	0.314	0.609
X₁₃	-0.365	6.531E-02	0.448	0.252

舵机	健康状态	亚健康状态	危险状态	故障状态
健康等级划分范围	(0.895, 1]	(0.634, 0.895]	(0.317, 0.634]	[0, 0.317]

序号	特征1	特征2	…	特征13	舵机状态	状态标记
1	0.18	20	…	0.93	健康	A
2	0.15	18	…	0.94	健康	A
┇	┇	┇	…	┇	┇	┇
200	0.16	21	…	0.98	故障	D