1. 西安交通大学 机械工程学院,陕西,西安,710049
2. 重庆长安汽车股份有限公司,重庆,400000
3. 中车青岛四方机车车辆股份有限公司,山东,青岛,266111
4. 西安现代控制技术研究所,陕西,西安,710065
5. 西安近代化学研究所,陕西,西安,710065
收稿:2025-04-03,
网络首发:2026-07-20,
移动端阅览
杜明龙,万鋆,王保鑫,等. 基于改进Bootstrap方法的固体火箭发动机小样本系统可靠性评估[J/OL]. 兵工学报, 2026(2026-07-20). https://doi.org/10.12382/bgxb.2025.0239.
DU M L, WAN J, WANG B X, et al. System reliability assessment of solid rocket motors based on modified bootstrap method under small-sample conditions[J/OL]. Acta Armamentarii, 2026(2026-07-20). https://doi.org/10.12382/bgxb.2025.0239. (in Chinese)
杜明龙,万鋆,王保鑫,等. 基于改进Bootstrap方法的固体火箭发动机小样本系统可靠性评估[J/OL]. 兵工学报, 2026(2026-07-20). https://doi.org/10.12382/bgxb.2025.0239. DOI:
DU M L, WAN J, WANG B X, et al. System reliability assessment of solid rocket motors based on modified bootstrap method under small-sample conditions[J/OL]. Acta Armamentarii, 2026(2026-07-20). https://doi.org/10.12382/bgxb.2025.0239. (in Chinese) DOI:
为了解决小样本条件下固体火箭发动机系统的可靠性评估难题,提出基于改进Bootstrap方法的可靠度评估框架。通过发动机组件分解建立串联系统可靠性模型,分别处理成败型单元(二项分布)和寿命型单元(指数/威布尔/正态分布)。采用B-样条函数重构经验分布函数,结合
k
-means聚类剔除Bootstrap重采样中的异值点,实现寿命型单元参数估计误差率较传统方法降低60%(
n
=15时误差小于等于±5%)。建立发动机子系统置信下限与系统可靠度的联合约束模型,通过实例验证表明:系统可靠度置信下限可达0.8493(置信度0.95),较LM(列文伯格-马夸尔特)方法提升15.4%。该方法可有效解决小样本、多失效模式下串联系统的可靠性评估问题,为固体火箭发动机的可靠性提升提供理论支撑。
A reliabilityassessmentframework based on an improved Bootstrap method is proposed to address the reliability assessment challenges of solid rocket engine systems under small-sample conditions.Aseries system reliability model is establishedby decomposingtheengine components
which separately handles the success-failure units characterized by binomial distribution and the lifetime units characterized by exponential
Weibull or normal distributions.Anempirical distribution functionisreconstructedusing a B-spline function
andtheoutliers in Bootstrap resamplingare eliminatedutilizing k-means clustering
thusreducingthe parameter estimation error for lifetime units by 60% (with error less than or equal to ±5% when
n
=15)compared to traditional methods. A joint constraint modelfor theconfidence limitsofengine subsystemandthesystem reliability is developed. Thevalidationthrough examples showsthat thelower bound ofsystem reliability confidence can reach 0.8493witha confidence levelof0.95
which is15.4%higher than that oftheLevenberg-Marquardt method. The proposed methodeffectively resolvesthereliability assessment problems for series systems with small samples and multiple failure modes
providing theoretical support for enhancingthereliabilityofsolid rocketmotor.
王有元. 基于Bayes方法及其改进的无失效数据和小子样产品可靠性评估[D]. 成都:电子科技大学,2022.
WANG Y Y. Reliability evaluation of the products with zero-failure data and small sample based on bayes method and its improvement[D].Chengdu: University of Electronic Science and Technology of China, 2022. (in Chinese)
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.
LIU H T, ZHANG Z H, DONG L. Bayesian acceptance test scheme for reliability of binomial products[J].Acta Armamentarii, 2016, 37(3): 565-569. (in Chinese)
WILSON A G, FRONCZVK K. Bayesian reliability: combining information[J]. Quality Engineering, 2017, 29(1): 119-129.
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.
WANG B, JIANG P, GUO B.Reliability evaluation of aerospace valves based on multi-source information fusion[J]. Acta Armamentarii, 2022, 43(1): 199-206. (in Chinese)
HUANG J D, HUANG Z Y, ZHAN X. Research on three-state reliability evaluation method of high reliability system based on multi-source prior information[J]. PeerJ Computer Science, 2023, 9: e1439.
CHENG T T, WANG X, LIU X T, et al. Uncertainty-based reliability analysis of cutters via improved Bayesian prior distribution[J]. Transactions of the Canadian Society for Mechanical Engineering, 2025, 49(2): 220-228.
AMALNERKAR E, LEE T H, LIM W. Reliability analysis using bootstrap information criterion for small sample size response functions[J] Structural and Multidisciplinary Optimization, 2020, 62(6): 2901-2913.
张震, 刘俭辉, 赵成, 等. 基于Bootstrap的小样本可靠性评估方法[J]. 兰州理工大学学报, 2022, 48(1): 39 -44.
ZHANG Z, LIU J H, ZHAO C, et al. A small sample reliability assessment method based on bootstrap[J]. Journal of Lanzhou University of Technology, 2022, 48(1): 39 -44. (in Chinese)
刘帼巾, 王泽, 李想, 等. 基于改进Bootstrap-Bayes的电子式剩余电流动作断路器可靠性评估[J]. 电工技术学报, 2022, 37(16): 4250-4258.
LIU G J, WANG Z, LI X, et al.Reliability evaluation of electronic residual current operated circuit breakers based on improved bootstrap-Bayes[J].Transactions of China Electrotechnical Society, 2022, 37(16):4250-4258. (in Chinese)
韩思杰, 王海清, 郑威, 等. 多重定时截尾数据下石化安全设备可靠度估计[J]. 计算机集成制造系统, 2023, 29(4): 1107-1114.
HAN S J, WANG H Q, ZHENG W, et al.Reliability estimation for petrochemical safety devices under multiple timing censored data[J]. Computer Integrated Manufacturing Systems, 2023, 29(4): 1107-1114. (in Chinese)
YOU D Z, LIU S, LI F K, et al.Reliability assessment method based on small sample accelerated life test data[J]. Eksploatacja I Niezawodność–Maintenance and Reliability, 2025, 27(1):192170.
WANG B X.Unbiased estimations for the exponential distribution based on step-stress accelerated life-testing data[J]. Applied Mathematics and Computation, 2006, 173(2): 1227-1237.
汤礼东, 宋保维, 李正, 等. 基于信息熵理论的小子样模糊可靠性评定方法[J]. 弹箭与制导学报, 2005, 25(1): 214-216.
TANG L D, SONG B W, LI Z, et al. A fuzzy reliability evaluation method for sub-sample products based on information entropy theory[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2005, 25(1): 214-216. (in Chinese)
LI Z A, FU H M, WU Q. Reliability assessment for a spacecraft landing buffer mechanism based on small sample data[J]. Machines, 2023, 11(9): 917.
ZHANG Y Z, HAN F, YANG F, et al. Reliability analysis of small-sample failure data for random truncation high-voltage relay[J]. Applied Sciences, 2024, 14(11): 4950.
李学京. 置信分布的贝塔分布近似及其在可靠性统计中的应用[J]. 强度与环境, 2007, 34(2): 17-23.
LI X J.Beta distribution approximation of confidence distributions and application in reliability statistics[J]. Structure & Environment Engineering, 2007, 34(2): 17-23. (in Chinese)
冯志刚, 李静, 高普云, 等.贝塔分布在数据转换中的应用及其优化分布参数确定[J].机械强度, 2011, 33(4): 554-557.
FENG Z G, LI J, GAO P Y, et al. Application of beta distribution in data convert and its optimize parameter ascertain[J]. Journal of Mechanical Strength, 2011, 33(4): 554-557. (in Chinese)
傅惠民, 李子昂, 郭建超.串联系统小样本可靠度直接评估方法[J].机电产品开发与创新, 2024, 37(4): 1 -5.
FU H M, LI Z A, GUO J C.Direct assessment method for series system reliability based on small sample data[J]. Development & Innovation of Machinery & Electrical Products, 2024, 37(4): 1 -5. (in Chinese)
孙权, 周星, 冯静, 等.寿命分布的参数Bootstrap拟合优度检验方法[J]. 国防科技大学学报, 2014,36(6): 112 -116.
SUN Q, ZHOU X, FENG J, et al. Goodness-of-fit test for life distributions based on parametric bootstrap[J]. Journal of National University of Defense Technology, 2014,36 (6): 112 -116. (in Chinese)
孔丹莉, 丁元林.非参数bootstrap方法及其应用[J]. 数理医药学杂志, 2006, 19(3): 232-233.
KONG D L, DING Y L. Non-parametric bootstrap method for validation stabilities of parameters of statistical model[J]. Journal of Mathematical Medicine, 2006, 19(3): 232-233. (in Chinese)
王森, 刘琛, 邢帅杰. K-means聚类算法研究综述[J].华东交通大学学报, 2022, 39(5): 119-126.
WANG S, LIU C, XING S J. Review on k-means clustering algorithm[J]. Journal of East China Jiaotong University, 2022, 39(5): 119-126. (in Chinese)
LIANG F M, KIM J S, SONG Q F. A bootstrap metropolis–hastings algorithm for bayesian analysis of big data[J]. Technometrics, 2016, 58(3): 304-318.
0
浏览量
0
下载量
0
CNKI被引量
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024360号