证据理论与贝叶斯网络相结合的可靠性分析方法
锁斌1,2曾超1,程永生1,李军1
1.中国工程物理研究院电子工程研究所,四川绵阳621900;
2.中国工程物理研究院北京研究生部,北京100088
摘 要:针对可靠性分析中存在的认知不确定性问题,将证据理论引入到贝叶斯网络。给出了存在认知不确定性时故障树向贝叶斯网络的转换方法,以及基于信任测度和似然测度求解顶事件发生概率的方法。研究了三种重要度的求解方法,同时提出了一个重要概念——认知重要度,给出了其实际意义和计算方法。最后,运用所提出方法对某导弹发动机进行了可靠性分析,结果表明,该方法增强了贝叶斯网络处理不确定性信息的能力,简单有效且可以得到更丰富的信息。
可靠性;可靠性分析;证据理论;贝叶斯网络;认知不确定性
TB114.3 A10. 3969/j. issn. 1001-506X. 2011.10. 39
Reliability analysis based on evidence theory and Bayesian networks methodSUO BinZENG ChaoCHENG Yong-shengLI Jun
2010-08-302011-01-06
“十一五”行业重点预研项目资助课题
锁斌(1979-),男,工程师,博士研究生,主要研究方向为不确定性信息处理、系统可靠性分析与评估。E-mail: suo.y.y@163.com
节点模型
件的故障@@[1] Bobbio A, Ciancamerla E, Franceschinis G, et al. Sequential application of heterogeneous models for the safety analysis of a control system: a case study[J]. Reliability Engineering & System Safety, 2003,81(3) : 269 - 280.
@@[2] Boudali H, Dugan J B. A discrete-time Bayesian network relia bility modeling and analysis framework[J]. Reliability Engi neering & System Safety, 2005,87 (3) : 337 - 349.
@@[3] Montani S, Portinale L, Bobbio A. Radyban: a tool for reliabili ty analysis of dynamic fault trees through conversion into dynamic Bayesian networks[J]. Reliability Engineering & Sys tem Safety ,2008,93(7) :922 - 932.
@@[4] Doguc O, Ramirez M, Jose E. A generic method for estimating system reliability using Bayesian networks [ J ]. Reliability Engineering & System Safety, 2009,94 (2) : 542 - 550.@@[5] Hichem B, Joanne B D. A continuous-time Bayesian network reliability modeling and analysis framework[J]. IEEE Trans. on Reliability ,2006,55(1) :86 - 97.
@@[6]梁家荣,花仁杰.评估STAR网络可靠性的新方法[J].系统工程 与电子技术,2010,32(2):419 - 422.(Liang J R, Hua R J.New method used for evaluating reliability of STAR networks[J]. Sys tems Engineering and Electronics ,2010,32(2):419- 422. )
@@[7] David M, Martin N, Norman F. Improved reliability modeling using Bayesian networks and dynamic discretization[J]. Relia bility Engineering & System Safety ,2010,95(4) :412 - 425.@@[8] Simon C, Weber C, Evsukoff A. Bayesian networks inference algorithm to implement Dempster Shafer theory in reliability analysis[J]. Reliability Engineering & System Safety, 2008, 93(7) :950 -963.
@@[9]赵书强,程德才,刘璐.结合D-S证据推理的贝叶斯网络法在 配电网可靠性评估中的应用[J].电工技术学报,2009,24(7):134 - 138. (Zhao S Q, Cheng D C, Liu L. Reliability evaluation of power distribution system based on D-S evidence inference and Bayesian networks method[J]. Transactions of China Electrotechnical Society ,2009,24(7) : 134 - 138. )
@@[10]许丽佳,王厚军,龙兵.基于贝叶斯网络的复杂系统故障预 测[J].系统工程与电子技术,2008,30(4):197 - 201.(Xu L J, Wang H J, Long B. Fault prediction of complex systems based on Bayesian network[J]. Systems Engineering and Electronics, 2008,30(4) : 197- 201. )@@[11]厉海涛,金光,周忠宝.基于贝叶斯网络的动量轮可靠性建模 与评估[J].系统工程与电子技术,2009,31(2):484-488.(Li H T, Jin G, Zhou Z B. Momentum wheel reliability modeling and assessment using Bayesian network[J]. Systems Engineer
ing and Electronics ,2009,31(2) :484 - 488. )
@@[12]厉海涛,金光,周经伦,等.贝叶斯网络推理算法综述[J].系 统工程与电子技术,2008, 30(5):157- 161.(Li H T, Jin G,
Zhou J L, et al. Survey of Bayesian network inference algo rithms[J]. Systems Engineering and Electronics ,2008,30(5) : 157 - 161. )
@@[13] Harmanee D, Klir G J. Measuring total uncertainty in Dempster Shafer theory: a novel approach[J]. International Journal of Gen
eral Systems, 1997,22(4) : 405 - 419.
@@[14] Mohamed A B, Yves D S, Ahmed F, et al. Building a binary outranking relation in uncertain, imprecise and multi-experts contexts: the application of evidence theory[J]. International Journal of Approximate Reasoning ,2009,50(8) : 1259 - 1278.@@[15]叶清,吴晓平,翟定军.一种基于能量函数的证据合成算法[J]. 系统工程与电子技术,2010,32(3):566 -569.(Ye Q,Wu X P, Zhai D J. Combination algorithm for evidence theory utilizing
energy function [ J ]. Systems Engineering and Electronics, 2010,32(3) :566 - 569. )
@@[16] Yakov B H. Uncertainty, probability and information-gaps[J]. Reliability Engineering and System Safety, 2004,85 ( 1 - 3) : 249 - 266.
@@[17] Denys Y, Frank H K, Yakov B H, et al. Detection capacity, information gaps and the design of surveillance programs for invasive forest peats[J]. Journal of Environmental Manage ment ,2010,91(12) :2535 - 2546.
@@[18] Carl M K, David H. MSBNx: A component-centric toolkit for
modeling and inference with Bayesian networks [R]. Seattle: Microsoft Corporation, 2001.下载本文