面向复杂系统的三维Bayes网络测试性验证模型

史贤俊; 王康; 肖支才; 龙玉峰; 陈垚

doi:10.13700/j.bh.1001-5965.2018.0663

面向复杂系统的三维Bayes网络测试性验证模型

doi: 10.13700/j.bh.1001-5965.2018.0663

1.
海军航空大学, 烟台 264001
2.
海军研究院, 北京 100161

详细信息

作者简介:
史贤俊男, 博士, 教授。主要研究方向:自动测试与故障诊断, 测试性设计、验证与评估

王康男, 博士研究生。主要研究方向:测试性设计、验证与评估

肖支才男, 博士, 副教授。主要研究方向:自动测试与故障诊断, 测试性设计、验证与评估

龙玉峰男, 博士研究生。主要研究方向:测试性设计、验证与评估

陈垚男, 硕士, 研究员。主要研究方向:测试与故障诊断

通讯作者:
史贤俊, E-mail: sxjaa@sina.com

中图分类号: V240.2;TJ06
计量
- 文章访问数: 693
- HTML全文浏览量: 172
- PDF下载量: 347
- 被引次数: 0
出版历程
- 收稿日期: 2018-11-19
- 录用日期: 2018-02-02
- 网络出版日期: 2019-07-20

Three-dimensional Bayes network testability verification model for complex systems

1.
Naval Aviation University, Yantai 264001, China
2.
Naval Research Institute, Beijing 100161, China

More Information

Corresponding author: SHI Xianjun, E-mail: sxjaa@sina.com

摘要

摘要:
针对当前武器装备复杂的系统结构，现有基于装备整机系统测试性先验信息的测试性验证方法难以适用，基于分系统测试性先验信息的测试性验证方法不能系统有效地处理先验信息，导致测试性验证结果可信度不高的问题，提出一种面向复杂系统的三维Bayes网络测试性验证模型。该模型能充分运用装备各层级结构中所蕴含的条件独立性，有效降低构建Bayes网络模型的复杂度，同时能融合装备各层级单元的先验信息。通过给出的三维Bayes网络的条件概率学习方法及G/M-H算法，由底层单元数据通过模型逐步向上融合，得到顶层测试性指标的后验分布，进一步利用顶层后验分布求取故障样本量。结果表明：该模型能充分考虑复杂系统的系统结构及各层级单元先验信息，并能通过模型推理得到的指标后验分布达到有效减少测试性验证故障样本量的目的。
- 先验信息 /
- 测试性验证 /
- 复杂系统 /
- 三维Bayes网络 /
- G/M-H算法 /
- 故障样本量
Abstract:
In view of the complicated system structure of current weapon equipment, the existing testability verification method based on the testability prior information of the equipment system is difficult to apply, and the testability verification method based on the testability prior information of the subsystem cannot process the prior information effectively, which lead to the low credibility of the testability verification results, so a three-dimensional Bayes network testability verification model for complex systems is proposed. The model can fully utilize the conditional independence contained in the various hierarchical structures of the equipment, effectively reduce the complexity of constructing the Bayesian network model, and at the same time integrate the prior information of each hierarchical unit. Through the given conditional probability learning method and G/M-H algorithm of the three-dimensional Bayes network, the underlying unit data can be integrated through the model to obtain the posterior distribution of the top-level testability indicators, and the top-level posterior distribution is further used to obtain the fault sample size. The results show that the model can fully consider the system structure of the complex system and the prior information of each hierarchical unit, and the posterior distribution of the testability indicators can be used to reduce the fault sample size of testability verification.
- prior information /
- testability verification /
- complex system /
- three-dimensional Bayes network /
- G/M-H algorithm /
- fault sample size

HTML全文

图 1 飞控系统三维Bayes网络模型

Figure 1. Three-dimensional Bayes network model of flight control system

下载: 全尺寸图片幻灯片

图 2 先验-后验概率密度函数对比

Figure 2. Comparison of prior-posterior probability density function

下载: 全尺寸图片幻灯片

图 3 不同层次节点后验概率密度函数对比

Figure 3. Comparison of posterior probability density function at different hierarchical nodes

下载: 全尺寸图片幻灯片

图 4 基于后验分布确定故障样本量算法实施流程

Figure 4. Algorithm implementation process for determining fault sample size based on posterior distribution

下载: 全尺寸图片幻灯片

表 1 系统实物试验数据

Table 1. Physical test data of system

参数	故障样本量	失败次数
数值	10	1

下载: 导出CSV

表 2 LRU实物试验数据

Table 2. Physical test data of LRU

LRU模块	故障样本量	失败次数
电缆网络	5	0
总线网络	3	1
弹上计算机	9	1
惯测组合	14	2
舵等效器	8	1
综合控制器	4	1

下载: 导出CSV

表 3 SRU实物试验数据

Table 3. Physical test data of SRU

SRU模块	故障样本量	失败次数
线加速度测量组合	5	1
角速度测量组合	5	1
二次电源	4	0
信息处理电路	2	0
弹机供电	2	0

下载: 导出CSV

表 4 综合控制器检测试验数据

Table 4. Detection test data of integrated controller

综合控制器	故障样本量	失败次数
地面测试1	4	0
地面测试2	4	0

下载: 导出CSV

表 5 各状态条件概率

Table 5. Conditional probability of each state

可检测部件数	层次节点
可检测部件数	N_{(0, 0, 0)}	N_{(1, 0, 1)}/N_{(0, 2, 1)}	N_{(0, 3, 1)}
0	R₁:U(0, 0.2)	R₈:U(0, 0.2)	R₁₁:U(0, 0.2)
1	R₂:U(0.1, 0.3)	R₉:U(0.6, 0.8)	R₁2:U(0.4, 0.6)
2	R₃:U(0.3, 0.5)	R₁₀:U(0.8, 1)	R₁₃:U(0.7, 0.9)
3	R₄:U(0.5, 0.6)		R₁₄:U(0.9, 1)
4	R₅:U(0.6, 0.8)
5	R₆:U(0.8, 0.9)
6	R₇:U(0.9, 1)

下载: 导出CSV

表 6 相关参数后验分布

Table 6. Posterior distribution of related parameters

参数	均值	标准差	分位数
参数	均值	标准差	2.5%	5%	50%	95%	97.5%
K	15.485	3.790	9.339	10.033	15.091	22.294	24.108
ε	0.876	0.046	0.770	0.791	0.881	0.944	0.952
P(N_{(0, 2, 1)}=1)	0.896	0.043	0.801	0.823	0.898	0.961	0.970
P(N_{(0, 3, 1)}=1)	0.886	0.046	0.782	0.804	0.890	0.955	0.964
P(N_{(1, 0, 1)}=1)	0.897	0.041	0.808	0.827	0.898	0.961	0.970
P(N_{(0, 0, 0)}=1)	0.876	0.036	0.799	0.814	0.878	0.931	0.941

下载: 导出CSV

参考文献(16)

[1]	石君友.测试性设计分析与验证[M].长沙:国防工业出版社, 2011. SHI J Y.Testability design analysis and verification[M].Chang-sha:National Defense Industry Press, 2011(in Chinese).
[2]	U.S.Department of Defense.Military standard testability program for electronic systems and equipments: MIL-STD-2165A[S].Washington, D.C.: U.S.Department of Defense, 1993.
[3]	中国人民解放军总装备部.装备测试性工作通用要求: GJB 2547A-2012[S].北京: 总装备部军标出版发行部, 2012. General Armament of PLA.General requirement for materiel testability program: GJB 2547A-2012[S].Beijing: General Armament Department Military Standards Publication and Distribution Department, 2012(in Chinese).
[4]	U.S.Department of Defense.Maintainability verification/demonstration/evaluation: MIL-STD-471A-1973[S].Washington, D.C.: U.S.Department of Defense, 1973.
[5]	石君友, 纪超, 李海伟.测试性验证技术与应用现状分析[J].测控技术, 2012, 31(5):29-32. doi: 10.3969/j.issn.1000-8829.2012.05.007 SHI J Y, JI C, LI H W.Analysis of testability verification technology and application status[J].Measurement & Control Technology, 2012, 31(5):29-32(in Chinese). doi: 10.3969/j.issn.1000-8829.2012.05.007
[6]	田仲, 石君友.现有测试性验证方法分析与建议[J].质量与可靠性, 2006(2):47-51. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=QK200602236937 TIAN Z, SHI J Y.Analysis and recommendations of existing testability verification methods[J].Quality and Reliablity, 2006(2):47-51(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=QK200602236937
[7]	李天梅, 邱静, 刘冠军.利用研制阶段试验数据制定测试性验证试验方案新方法[J].机械工程学报, 2009, 45(8):52-57. http://d.old.wanfangdata.com.cn/Periodical/jxgcxb200908009 LI T M, QIU J, LIU G J.New methodology for determining testability integrated test scheme with test data in the development stages[J].Journal of Mechanical Engineering, 2009, 45(8):52-57(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/jxgcxb200908009
[8]	李天梅, 邱静, 刘冠军.基于Bayes变动统计理论的测试性外场统计验证方法[J].航空学报, 2010, 31(2):335-341. http://d.old.wanfangdata.com.cn/Periodical/hkxb201002017 LI T M, QIU J, LIU G J.Research on testability field statistics verification based on Bayes inference theory of dynamic population[J].Acta Aeronautica et Astronautica Sinica, 2010, 31(2):335-341(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/hkxb201002017
[9]	邓露, 许爱强, 李文海, 等.基于Bayesian理论的测试性验证试验方案[J].南京理工大学学报(自然科学版), 2014, 38(6):775-780. doi: 10.3969/j.issn.1005-9830.2014.06.012 DENG L, XU A Q, LI W H, et al.Testability demonstration test scheme based on Bayesian theory[J].Journal of Nanjing University of Science and Technology, 2014, 38(6):775-780(in Chinese). doi: 10.3969/j.issn.1005-9830.2014.06.012
[10]	王敏, 杨江平, 卢雷, 等.利用分系统数据制定整机测试性验证试验方案[J].现代防御技术, 2015, 43(5):213-217. doi: 10.3969/j.issn.1009-086x.2015.05.034 WANG M, YANG J P, LU L, et al.Determining testability demonstration test scheme with subsystem data[J].Modern Defence Technology, 2015, 43(5):213-217(in Chinese). doi: 10.3969/j.issn.1009-086x.2015.05.034
[11]	常春贺, 杨江平, 胡亮.基于Bayes理论的复杂装备测试性评估方法[J].火力指挥与控制, 2012, 37(11):173-176. http://d.old.wanfangdata.com.cn/Periodical/hlyzhkz201211046 CHANG C H, YANG J P, HU L.Study on testability evaluation method for complex equipment based on Bayes theory[J].Fire Control & Command Control, 2012, 37(11):173-176(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/hlyzhkz201211046
[12]	张西山, 黄考利, 闫鹏程, 等.基于验前信息的测试性验证试验方案确定方法[J].北京航空航天大学学报, 2015, 41(8):1505-1512. https://bhxb.buaa.edu.cn/CN/abstract/abstract13363.shtml ZHANG X S, HUANG K L, YAN P C, et al.Method of confirming testability verification test scheme based on prior information[J].Journal of Beijing University of Aeronautics and Astronantics, 2015, 41(8):1505-1512(in Chinese). https://bhxb.buaa.edu.cn/CN/abstract/abstract13363.shtml
[13]	郑应荣.系统级层次化测试性建模与分析[D].哈尔滨: 哈尔滨工业大学, 2014. http://www.wanfangdata.com.cn/details/detail.do?_type=degree&id=D591285 ZHENG Y R.Testablity modeling and analysis of hierarchical system[D].Harbin: Harbin Institute of Technology, 2014(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=degree&id=D591285
[14]	王京, 李天梅, 何华锋, 等.多源测试性综合数据等效折合模型与方法研究[J].兵工学报, 2017, 38(1):151-159. doi: 10.3969/j.issn.1000-1093.2017.01.020 WANG J, LI T M, HE H F, et al.Research on multi-source data equivalent methods for testability integrated evaluation[J].Acta Armamentarii, 2017, 38(1):151-159(in Chinese). doi: 10.3969/j.issn.1000-1093.2017.01.020
[15]	刘钰, 韩峰, 闫凯, 等.基于贝叶斯网络的分层系统可靠性分析[J].航空动力学报, 2016, 31(6):1385-1392. http://d.old.wanfangdata.com.cn/Periodical/hkdlxb201606014 LIU Y, HAN F, YAN K, et al.Reliability analysis of hierarchical systems based on Bayesian network[J].Journal of Aerospace Power, 2016, 31(6):1385-1392(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/hkdlxb201606014
[16]	王超.虚实结合的测试性试验与综合评估技术[D].长沙: 国防科学技术大学, 2014. http://cdmd.cnki.com.cn/Article/CDMD-90002-1016922110.htm WANG C.Testability test and integrated evaluation technology with virtual-physical test[D].Changsha: National University of Defense Technology, 2014(in Chinese). http://cdmd.cnki.com.cn/Article/CDMD-90002-1016922110.htm