A Reliability Modeling Method for Non-failure Data Link of Cryogenic Valve
-
摘要: 针对无失效数据环节的可靠性评估时,采用单一模型难以同时得到参数的点估计和置信区间估计,而采用不同方法分别进行点估计和区间估计会造成结果的一致性问题, 本文针对在无失效数据情形下,对低温阀门填料环节进行可靠性分析,提出了一种运用多层bayes方法得到产品可靠度的点估计,综合bootstrap抽样法从产品的寿命概率分布中重新抽取样本,与矩法结合得出低温阀门填料环节的可靠度区间估计的可靠性建模方法。该方法根据低温阀门实际运行工况,确定多层bayes方法中取值上限参数c的值,进而得到低温阀门填料环节的寿命概率分布曲线,再利用bootstrap法从寿命概率分布中重新抽取新样本,新样本采用矩法获得低温阀门填料环节可靠度的区间估计,并与置信限方法得到的区间估计进行对比。结果表明:在威布尔分布条件下,新模型提高了可靠度区间估计精度,为无失效数据环节可靠性评估提供了理论基础。
-
关键词:
- 无失效数据环节 /
- 多层bayes /
- bootstrap法 /
- 低温阀门可靠性评估
Abstract: In evaluating the reliability of a non-failure data link, it is difficult to estimate the points of parameters and their confidence interval at the same time by using a single model, and different methods for point and interval estimation may cause the inconsistency of results. This paper carried out the reliability analysis of the packing link of a cryogenic valve under the condition of non-failure data. A point estimation method of product reliability was proposed with the multilayer Bayes method. Samples were extracted from product life probability distribution with the bootstrap sampling method. Combined with the moment method, a reliability modeling method for estimating the interval reliability of the packing link of a cryogenic valve is obtained. The method was based on actual operation conditions to determine the value of the range parameter c with the multilayer Bayes method. Thus, the service life of the cryogenic valve′s packing link probability distribution curve was extracted from the life probability distribution of new samples through reusing the bootstrap method. New samples of the cryogenic valve′s packing link reliability interval estimation were obtained with the moment method. The results are compared with the interval estimation by using the confidence limit method. They show that the new model improves the accuracy of reliability interval estimation under the Weibull distribution, providing a theoretical basis for the reliability evaluation of non-failure data links. -
表 1 低温截止阀填料环节无失效试验数据
Table 1. Test data of low-temperature stop valve filling failur
截尾次序i 截尾次数ti/次 样本数ni/个 未失效总数si/个 1 2 750 2 20 2 2 900 2 18 3 3 050 2 16 4 3 200 2 14 5 3 350 2 12 6 3 500 2 10 7 3 650 2 8 8 3 800 2 6 9 3 950 2 4 10 4 100 2 2 表 2 不同c值下的多层Bayes累计失效率
Table 2. Cumulative failure rate of multilayer Bayes under different C values
累计失效率 c=2 c=3 c=4 c=5 c=6 c=7 p1 0.044 3 0.043 2 0.042 1 0.041 1 0.040 1 0.039 1 p2 0.048 7 0.047 3 0.046 0 0.044 8 0.043 6 0.042 5 p3 0.053 9 0.052 3 0.050 7 0.049 2 0.047 8 0.046 5 p4 0.060 4 0.058 4 0.056 4 0.054 6 0.052 9 0.051 3 p5 0.068 8 0.066 1 0.063 7 0.061 4 0.059 3 0.057 3 p6 0.079 7 0.076 2 0.073 0 0.070 1 0.067 4 0.064 9 p7 0.094 9 0.090 0 0.085 6 0.081 7 0.078 2 0.075 0 p8 0.117 2 0.110 0 0.103 6 0.098 1 0.093 2 0.088 8 p9 0.153 2 0.141 4 0.131 5 0.123 1 0.115 9 0.109 6 p10 0.221 5 0.199 1 0.181 3 0.166 9 0.155 1 0.145 1 表 3 多层Bayes下各截尾时刻的累计失效率
Table 3. Cumulative failure rate of each truncated time under the multi-layer Bayes
累计失效率 c=90 c=91 c=92 c=93 c=94 极差 p1 0.015 6 0.015 5 0.015 4 0.015 3 0.015 2 0.04 p2 0.016 3 0.016 2 0.016 1 0.016 0 0.015 9 0.04 p3 0.017 0 0.016 9 0.016 8 0.016 7 0.016 6 0.04 p4 0.018 0 0.017 8 0.017 7 0.017 6 0.017 5 0.05 p5 0.019 0 0.018 9 0.018 8 0.018 7 0.018 5 0.05 p6 0.020 3 0.020 2 0.020 0 0.019 9 0.019 8 0.05 p7 0.021 9 0.021 7 0.021 6 0.021 4 0.021 3 0.06 p8 0.024 0 0.023 8 0.023 6 0.023 5 0.023 3 0.07 p9 0.026 9 0.026 7 0.026 5 0.026 3 0.026 1 0.08 p10 0.031 6 0.031 3 0.031 1 0.030 8 0.030 6 0.10 -
[1] LIU J F, YIN Y C, FU G Z, et al. Notice of Retraction: a fusion method of zero-failure data in different environments for reliability assessment of success-failure type products[C]//International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering. Chengdu: IEEE, 2013: 1102-1105. [2] 韩明. 无失效数据情形可靠性参数的估计和调整[J]. 应用数学, 2006, 19(2): 325-330. doi: 10.3969/j.issn.1001-9847.2006.02.016HAN M. Estimation and rectification of reliability parameters in the case of zero-failure data[J]. Mathematica Applicata, 2006, 19(2): 325-330. (in Chinese) doi: 10.3969/j.issn.1001-9847.2006.02.016 [3] NAGATA H, LI Y G, MAACK D R, et al. Reliability estimation from zero-failure LiNbO3 modulator bias drift data[J]. IEEE Photonics Technology Letters, 2004, 16(6): 1477-1479. doi: 10.1109/LPT.2004.827857 [4] BEN ALI J, CHEBEL-MORELLO B, SAIDI L, et al. Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network[J]. Mechanical Systems and Signal Processing, 2015, 56-57: 150-172. [5] MA M, CHEN X F, WANG S B, et al. Bearing degradation assessment based on Weibull distribution and deep belief network[C]//2016 International Symposium on Flexible Automation (ISFA). Cleveland: IEEE, 2016: 382-385. [6] YANG J W, WANG J H, XIE Y D. Bayesian method for reliability assessment based on zero-failure data under small sample size: application for high speed railway vehicle[J]. Information Technology Journal, 2013, 12(21): 6203-6207. doi: 10.3923/itj.2013.6203.6207 [7] BREMERMAN M V. Practical Bayesian methods for determining device failure rates from zero-failure data[C]//Reliability & Maintainability Symposium. Orlando: IEEE, 2013: 1-6. [8] 茆诗松, 夏剑锋, 管文琪. 轴承寿命试验中无失效数据的处理[J]. 应用概率统计, 1993, 9(3): 326-331. https://www.cnki.com.cn/Article/CJFDTOTAL-YYGN199303014.htmMAO S S, XIA J F, GUAN W Q. The reliability analysis of zero-failure data for bearing life test[J]. Chinese Journal of Applied Probability and Statistics, 1993, 9(3): 326-331. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YYGN199303014.htm [9] HAN M. Bayesian estimation and hierarchical Bayesian estimation of zero-failure data[1]. Chinese Quarterly Journal of Mathematics, 2001, 16(1): 65-70. [10] 刘海涛, 张志华. 威布尔分布无失效数据的Bayes可靠性分析[J]. 系统工程理论与实践, 2008, 28(11): 103-108. https://www.cnki.com.cn/Article/CJFDTOTAL-XTLL200811015.htmLIU H T, ZHANG Z H. Bayesian reliability analysis of Weibull zero failure data[J]. Systems Engineering-Theory & Practice, 2008, 28(11): 103-108. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XTLL200811015.htm [11] 韩明. 多层先验分布的构造及其应用[J]. 运筹与管理, 1997, 6(3): 31-40. https://www.cnki.com.cn/Article/CJFDTOTAL-YCGL703.007.htmHAN M. The structure of hierarchical prior distribution and it's applications[J]. Operations Research and Management Science, 1997, 6(3): 31-40. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YCGL703.007.htm [12] 韩明. 产品无失效数据的综合处理[J]. 机械工程学报, 2003, 39(2): 129-132. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB200302028.htmHAN M. Synthesized process for zero-failure data of the products[J]. Chinese Journal of Mechanical Engineering, 2003, 39(2): 129-132. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB200302028.htm [13] 蔡国梁, 吴来林, 唐晓芬. 双超参数无失效数据的E-Bayes可靠性分析[J]. 江苏大学学报(自然科学版), 2010, 31(6): 736-739. https://www.cnki.com.cn/Article/CJFDTOTAL-JSLG201006027.htmCAI G L, WU L L, TANG X F. E-Bayes reliability analysis of double hyperparameters zero failure data[J]. Journal of Jiangsu University (Natural Science Edition), 2010, 31(6): 736-739. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSLG201006027.htm [14] 傅惠民, 张勇波. Weibull分布定时无失效数据可靠性分析方法[J]. 航空动力学报, 2010, 25(12): 2807-2810. https://www.cnki.com.cn/Article/CJFDTOTAL-HKDI201012025.htmFU H M, ZHANG Y B. Method of reliability analysis for time truncated zero-failure data based on Weibull distribution[J]. Journal of Aerospace Power, 2010, 25(12): 2807-2810. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HKDI201012025.htm [15] 韩明. 无失效数据情形可靠性参数的置信限[J]. 工程数学学报, 2004, 21(2): 245-248. https://www.cnki.com.cn/Article/CJFDTOTAL-GCSX200402019.htmHAN M. Confidence limit of reliability parameters in the case of zero-failure data[J]. Chinese Journal of Engineering Mathematics, 2004, 21(2): 245-248. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GCSX200402019.htm [16] 蒋仁斌, 姜殿玉. 基于无失效数据贮备系统可靠性的fiducial置信限[J]. 浙江大学学报(理学版), 2010, 37(6): 629-632. https://www.cnki.com.cn/Article/CJFDTOTAL-HZDX201006007.htmJIANG R B, JIANG D Y. The fiducial lower confidence limits of reliability for standby system based on zero-failure data[J]. Journal of Zhejiang University (Science Edition), 2010, 37(6): 629-632. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HZDX201006007.htm [17] 韩明. Weibull分布可靠性参数的置信限[J]. 机械强度, 2009, 31(1): 59-62. https://www.cnki.com.cn/Article/CJFDTOTAL-JXQD200901015.htmHAN M. Confidence limits of reliability parameters for Weibull distribution[J]. Journal of Mechanical Strength, 2009, 31(1): 59-62. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXQD200901015.htm [18] 贾祥, 王小林, 郭波. 极少失效数据和无失效数据的可靠性评估[J]. 机械工程学报, 2016, 52(2): 182-188. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201602028.htmJIA X, WANG X L, GUO B. Reliability assessment for very few failure data and zero-failure data[J]. Journal of Mechanical Engineering, 2016, 52(2): 182-188. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201602028.htm [19] 罗巍, 张春华, 谭源源, 等. 基于Bootstrap的可修系统贮存可用度近似置信下限评估方法[J]. 兵工学报, 2010, 31(3): 391-395. https://www.cnki.com.cn/Article/CJFDTOTAL-BIGO201003022.htmLUO W, ZHANG C H, TAN Y Y, et al. Estimating method of approximate confidence lower limits of repairable system storage availability based on bootstrap[J]. Acta Armamentarii, 2010, 31(3): 391-395. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BIGO201003022.htm [20] 李东兵, 胡文林. 基于无失效数据的某型发动机可靠性参数Bayes估计[J]. 海军航空工程学院学报, 2020, 35(5): 349-354. https://www.cnki.com.cn/Article/CJFDTOTAL-HJHK202005001.htmLI D B, HU W L. Bayesian estimations of reliability parameters on a certain engine based on zero failure data[J]. Journal of Naval Aviation University, 2020, 35(5): 349-354. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HJHK202005001.htm [21] LU Y, ZHENG J M, ZHAO C, et al. Risk assessment of a cryogenic globe valve by using combined group decision and fuzzy comprehensive evaluation[J]. Mathematical Problems in Engineering, 2021, 2021: 6666126. http://www.xueshufan.com/publication/3133158285 [22] JOSHI M, SEIDEL-MORGENSTERN A, KREMLING A. Exploiting the bootstrap method for quantifying parameter confidence intervals in dynamical systems[J]. Metabolic Engineering, 2006, 8(5): 447-455 [23] 李海洋, 谢里阳, 刘杰, 等. 无失效数据场合智能换刀机器人中轴承的可靠性评估[J]. 机械工程学报, 2019, 55(2): 186-194. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201902021.htmLI H Y, XIE L Y, LIU J, et al. Reliability evaluation of bearings in theintelligent robot for changing the hobwithout failure data[J]. Journal of Mechanical Engineering, 2019, 55(2): 186-194. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201902021.htm [24] BAIN L J. Inferences based on censored sampling from the Weibull or extreme-value distribution[J]. Technometrics, 1972, 14(3): 693-702 [25] 韩明. Weibull分布可靠性参数的置信限[J]. 机械强度, 2009, 31(1): 59-62. (查阅网上资料, 本条文献与第17条文献重复, 请确认)HAN M. Confidence limits of reliability parameters for Weibull distribution[J]. Journal of Mechanical Strength, 2009, 31(1): 59-62. (in Chinese) [26] LIANG R Z, WU W B, YU F, et al. Simplified method for evaluating shield tunnel deformation due to adjacent excavation[J]. Tunnelling and Underground Space Technology, 2018, 71: 94-105. [27] 夏新涛, 叶亮, 李云飞, 等. 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. https://www.cnki.com.cn/Article/CJFDTOTAL-BIGO201607022.htmXIA X T, YE L, LI Y F, et al. Reliability evaluation based on hierarchical bootstrap maximum entropy method[J]. Acta Armamentarii, 2016, 37(7): 1317-1329. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BIGO201607022.htm