基于Bayes混合验前分布的成败型产品可靠性评估

doi:10.3969/j.issn.1000-1093.2016.03.016

兵工学报 ›› 2016, Vol. 37 ›› Issue (3): 505-511.doi: 10.3969/j.issn.1000-1093.2016.03.016

基于Bayes混合验前分布的成败型产品可靠性评估

张文杰^1,2，杨华波²，张士峰²

(1.92853部队, 辽宁兴城 125109； 2.国防科学技术大学航天科学与工程学院, 湖南长沙 410073)

收稿日期:2015-03-22 修回日期:2015-03-22 上线日期:2016-05-24
通讯作者: 张文杰 E-mail:zhangwenjie_0731@163.com
作者简介:张文杰(1991—)男硕士研究生

Reliability Assessment for Device with Only Safe-or-failure Pattern Based on Bayesian Hyprid Prior Approach

ZHANG Wen-jie^1,2， YANG Hua-bo²， ZHANG Shi-feng²

(1.Unit 92853 of PLA， Xingcheng 125109， Liaoning， China；2.School of Aerospace Science and Engineering， National University of Defense Technology， Changsha 410073， Hunan， China)

Received:2015-03-22 Revised:2015-03-22 Online:2016-05-24
Contact: ZHANG Wen-jie E-mail:zhangwenjie_0731@163.com

摘要/Abstract

摘要： 针对小子样成败型产品可靠性评估问题，引入混合验前分布构造方法，推导了Bayes混合验前分布下成败型产品可靠度参数的验后概率分布函数，研究了验前分布参数对于验后估计的影响，并总结了验前分布参数选择的一般性原则。分析对比了传统Bayes方法和混合验前分布方法的参数验后估计，其结果表明后者能够有效避免验前信息淹没现场信息的问题。对验后均方误差的分析表明混合验前分布方法能够一定程度上改善估计的效果。与幂验前方法的对比结果表明，当验前样本容量较大时，混合验前分布方法的估计效果优于幂验前方法。

关键词: 系统评估与可行性分析, 可靠性评估, 成败型, Bayes方法, 混合验前分布

Abstract: For the reliability evaluation of device with only safe-or-failure pattern, a hyprid prior approach is introduced, and the posteriori probability distribution function of reliability parameter is deduced by Bayesian method. The influence of prior distribution parameters on the posterior estimation is considered, and the general rules of choosing these parameters are summarized. The parameter posterior estimates of traditional Bayesian method and hyprid prior approach are compared. The results indicate that the hyprid prior approach can avoid the problem of that the prior data inundate the posteriori data effectively. The analysis of posteriori mean square error demonstrates that the hyprid prior approach can improve the performance of estimation to some extent. Through the comparison with power prior approach, it is proved that the estimation effect of hyprid prior approach is better than that of power prior approach, especially when prior sample size is larger.

Key words: system assessment and feasibility analysis, reliability assessment, safe-or-failure pattern, Bayesian method, hyprid prior approach

中图分类号:

TB114.3

张文杰，杨华波，张士峰. 基于Bayes混合验前分布的成败型产品可靠性评估[J]. 兵工学报, 2016, 37(3): 505-511.

ZHANG Wen-jie， YANG Hua-bo， ZHANG Shi-feng. Reliability Assessment for Device with Only Safe-or-failure Pattern Based on Bayesian Hyprid Prior Approach[J]. Acta Armamentarii, 2016, 37(3): 505-511.

参考文献

［1］刘晗，郭波. 研制阶段的成败型产品可靠性Bayes评估[J]．电子产品可靠性与环境试验，2006，24(5)：25-29.
LIU Han, GUO Bo. Bayes assessment for reliability of success or failure product in the development phases[J]. Electronic Product Reliability and Environmental Testing, 2006, 24(5): 25-29. (in Chinese)
[2］张士峰，杨华波，张金槐，等. 小样本成败型设备可靠性评估方法[J]．核动力工程，2006，27(5)：79-83.
ZHANG Shi-feng, YANG Hua-bo, ZHANG Jin-huai, et al. Reliability assessment methods with small-sample for device with only safe-or-failure pattern[J]. Nuclear Power Engineering, 2006, 27(5): 79-83. (in Chinese)
[3］张士峰，蔡洪. 固体火箭发动机性能可靠性评估的Bayes方法[J]．固体火箭技术，2003，26(4)：9-11.
ZHANG Shi-feng, CAI Hong. Bayesian approach of performance reliability assessment of solid rocket motors[J]. Journal of Solid Rocket Technology, 2003, 26(4): 9-11. (in Chinese)
[4］茆定远，薛大知. 核电站PSA分析中可靠性数据处理的贝叶斯方法[J]．核动力工程，2000，21(5)：451-455.
MAO Ding-yuan, XUE Da-zhi. The Bayesian method of data processing in nuclear power plant[J]. Nuclear Power Engineering, 2000, 21(5): 451-455. (in Chinese)
[5］毛昭勇，宋保维，胡海豹，等. 基于AMSAA增长模型的鱼雷系统Bayes可靠性分析[J]．兵工学报，2009，30(10)：1401-1404.
MAO Zhao-yong, SONG Bao-wei, HU Hai-bao, et al. The Bayes reliability evaluation method based on AMSAA model for torpedo system[J]. Acta Armamentarii, 2009, 30(10): 1401-1404. (in Chinese)
[6］韩明. 可靠性工程中参数的E-Bayes估计法及其应用[J]．兵工学报，2009，30(11)：1473-1476.
HAN Ming. E-Bayesian estimation method of parameter and its applications in reliability engineering[J]. Acta Armamentarii, 2009, 30(11): 1473-1476. (in Chinese)
[7］谭源源，张春华，陈循，等. 基于狄氏先验分布的机电产品主要失效模式贝叶斯分析[J]．兵工学报，2012，33(2)：209-213.
TAN Yuan-yuan, ZHANG Chun-hua, CHEN Xun, et al. Bayesian analysis based on dirichlet prior distribution of dominant failure modes for electromechanical products[J]. Acta Armamentarii, 2012, 33(2): 209-213. (in Chinese)
[8］ Zellner A. Information processing and Bayesian analysis[J]. Journal of Econometrics, 2002, 107(1): 41-45.
[9］ Ibrahim J G, Chen, M H, Sinha D, et al. On optimality properties of the power prior[J]. Journal of the American Statistical Association, 2003, 98(1): 204-213.
[10］ Ibrahim J G, Chen M H. Power prior distributions for regression models[J]. Statistical Science, 2000, 15(1): 46-60.
[11］杨华波，张士峰，蔡洪，等. 成败型产品可靠性评估的Bayes修正幂验前方法[J]．固体火箭技术，2009，32(2)：131-134.
YANG Hua-bo, ZHANG Shi-feng, CAI Hong, et al. Bayesian modified power prior approach for product reliability assessment with only safe-or failure pattern[J]. Journal of Solid Rocket Technology, 2009, 32(2): 131-134. (in Chinese)
[12］张士峰，樊树江，张金槐，等. 成败型产品可靠性的Bayes评估[J]．兵工学报，2001，22(2)：238-240.
ZHANG Shi-feng, FAN Shu-jiang, ZHANG Jin-huai, et al. Bayesian assessment for product reliability using pass-fail data[J]. Acta Armamentarii, 2001, 22(2): 238-240. (in Chinese)
[13］明志茂，陶俊勇，陈循，等. 基于混合Beta分布的成败型产品Bayes可靠性鉴定试验方案研究[J]．兵工学报，2008，29(2)：204-207.
MING Zhi-mao, TAO Jun-yong, CHEN Xun, et al. A Bayes plan of reliability qualification test based on the mixed Beta distribution for success/failure product[J]. Acta Armamentarii, 2008, 29(2): 204-207. (in Chinese)
[14］ Helminen A. Reliability estimation of safety-critical software-based systems using Bayesian networks, STUK-YTO-TR178[R].Helsinki, Finland: Radiation and Nuclear Safety Authority, 2001.
[15］杨华波，蔡洪，张士峰，等. 基于混合验前分布的制导精度评定方法[J]．航空学报，2009, 30(5): 855-860.
YANG Hua-bo, CAI Hong, ZHANG Shi-feng, et al. Evaluation of missile guidance precision based on hybrid prior distribution[J]. Acta Aeronautica et Astronautica Sinica, 2009, 30(5): 855-860. (in Chinese)

[1]	纪明，卜珺珺，马聪. 最大熵试验法对航天作动器输出可靠性的评估[J]. 兵工学报, 2022, 43(4): 919-923.
[2]	王博，蒋平，郭波. 基于多源信息融合的航天阀门可靠性评估[J]. 兵工学报, 2022, 43(1): 199-206.
[3]	宁小磊，吴颖霞，赵新. 融合仿真数据的小子样圆概率误差评估[J]. 兵工学报, 2021, 42(2): 388-398.
[4]	金俊坤，杨宁国，吕冬雪. 结合单元试验数据的指数型串联系统定时截尾试验可靠性评估方法[J]. 兵工学报, 2019, 40(8): 1756-1760.
[5]	李海洋，谢里阳，李铭，李强，钟海. 一种新的无失效数据可靠性评估方法研究[J]. 兵工学报, 2018, 39(8): 1622-1631.
[6]	郭志明，李长福，姬广振，刘勤，钱云鹏，胡冰甦. 改进布谷鸟算法在成败型产品可靠性抽样检验方案设计中的应用研究[J]. 兵工学报, 2017, 38(4): 758-765.
[7]	曹文斌，胡起伟，苏续军，赵建民. 随机共因失效条件下的多阶段任务成功概率评估研究[J]. 兵工学报, 2017, 38(4): 766-775.
[8]	苏续军, 吕学志. 基于离散事件仿真的多状态多阶段任务系统可靠性分析[J]. 兵工学报, 2017, 38(4): 776-784.
[9]	王京，李天梅，何华锋，徐从启. 多源测试性综合评估数据等效折合模型与方法研究[J]. 兵工学报, 2017, 38(1): 151-159.
[10]	闫华，高黎，王魁，漆磊. 大规模多阶段任务系统马尔可夫可靠性模型的存储和计算[J]. 兵工学报, 2016, 37(9): 1715-1720.
[11]	夏新涛，叶亮，李云飞，常振. 基于多层自助最大熵法的可靠性评估[J]. 兵工学报, 2016, 37(7): 1317-1329.
[12]	田恒，段富海，江秀红，桑勇. 基于准信息熵的测试性D矩阵故障诊断新算法[J]. 兵工学报, 2016, 37(5): 923-928.
[13]	刘海涛，张志华，董理. 成败型产品可靠性的Bayes验收方案研究[J]. 兵工学报, 2016, 37(3): 565-569.
[14]	高昂, 胡延苏. 基于概率模型的弹道导弹防御系统拦截方案优化与评估[J]. 兵工学报, 2016, 37(2): 379-384.
[15]	朱赛，蔡金燕，孟亚峰，李丹阳，潘刚. 具有故障细胞的胚胎电子阵列上目标电路评估[J]. 兵工学报, 2016, 37(11): 2120-2127.

基于Bayes混合验前分布的成败型产品可靠性评估

Reliability Assessment for Device with Only Safe-or-failure Pattern Based on Bayesian Hyprid Prior Approach

PDF

可视化

被引次数

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