性能退化双线性过程方法与成组试验方法的比较

王治华; 傅惠民; 黄蓉; 张勇波

doi:10.13224/j.cnki.jasp.2014.07.007

性能退化双线性过程方法与成组试验方法的比较

doi: 10.13224/j.cnki.jasp.2014.07.007

北京航空航天大学航空科学与工程学院, 北京 100191

基金项目:

国家自然科学基金（11202011）；国家重点基础研究发展计划（2012CB720000）；中央高校基本科研业务费专项资金（YWF-13-HK-11）

详细信息

作者简介:
王治华（1981-），女，辽宁辽阳人，讲师、硕士生导师，博士，主要从事可靠性工程、小样本技术研究。

中图分类号: V448;O231
计量
- 文章访问数: 1178
- HTML浏览量: 3
- PDF量: 819
- 被引次数: 0
出版历程
- 收稿日期: 2013-04-08
- 刊出日期: 2014-07-28

Comparison of bilinear process method and group test method for performance degradation

School of Aeronautic Science and Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 针对性能退化可靠性分析问题，将双线性过程方法与成组试验方法进行了对比分析.首先，从理论层面阐述了双线性过程方法和成组试验方法对性能退化数据的建模过程，可以发现：双线性过程方法通过将性能退化数据作为一个整体进行统计分析，能够避免两步估计造成的信息浪费，提高分析精度.其次，以窗雨刮器开关性能退化试验为例进行了对比分析，结果表明，双线性过程方法共有2.5%的试验数据位于概率为90%的百分位值曲线估计结果上方，符合工程实际需要，而成组试验方法共有15%的试验数据位于百分位值曲线估计结果上方.此外，基于残差分析的模型检验结果表明双线性过程方法更为合理.
- 性能退化 /
- 可靠性分析 /
- 双线性过程方法 /
- 成组试验方法 /
- 两步估计
Abstract: For the performance degradation reliability analysis, comparison of bilinear process method and group test method was conducted. The modeling procedure of these two methods was theoretically discussed. It can be found consequently that, the analysis precision of bilinear process method can be improved based on the one-stage estimation process, helping to avoid information waste. A reported window wiper switch performance degradation test was then considered to verify these two methods. Comparative analysis of the 10th percentile curve indicates that, the bilinear process method with 2.5% upper test data, can derive more reasonable results, compared with the group test method with 15% upper test data. In addition, model validation based on the residual analysis illustrates the effectiveness of the bilinear process method.
- performance degradation /
- reliability analysis /
- bilinear process method /
- group test method /
- two-stage estimation

HTML

参考文献(15)

[1]	Nair V N.Discussion of estimation of reliability in field performance studies[J].Technometrics,1988,30:379-383.
[2]	Ross S M.Stochastic processes[M].New York:John Wiley and Sons Incorporated,1983.
[3]	《现代应用数学手册》编委会.现代应用数学手册:概率统计与随机过程卷[M].北京:清华大学出版社,2004.
[4]	Nelson W.Analysis of performance degradation data from accelerated tests[J].Transactions on Reliability,1981,30(2):149-155.
[5]	Nelson W.Accelerated testing:statistical models,test plans,and data analysis[M].New York:John Wiley and Sons Incorporated,2004.
[6]	Wang W D,Dan D D.Reliability quantification of induction motors[C]//Proceedings Annual Reliability and Maintainability Symposium.Washington:Institute of Electrical and Electronics Engineers,2002:325-331.
[7]	傅惠民,吴琼.线性独立增量过程分析方法[J].航空动力学报,2010,25(4):930-935. FU Huimin,WU Qiong.Analysis method for linear process with independent increments[J].Journal of Aerospace Power,2010,25(4):930-935.(in Chinese)
[8]	傅惠民,吴琼.线性过程回归分析方法[J].机械强度,2010,32(4):600-605. FU Huimin,WU Qiong.Regression analysis method for linear process[J].Journal of Mechanical Strength,2010,32(4):600-605.(in Chinese)
[9]	Montgomery D C,Runger G C.Applied statistics and probability for engineers[M].3rd ed.New York:John Wiley and Sons Incorporated,2003.
[10]	Devore J L.Probability and statistics for engineering and the science[M].15th ed.Beijing:Higher Education Press,2004.
[11]	高镇同.疲劳应用统计学[M].北京:国防工业出版社,1986.
[12]	林洪桦.动态测试数据处理[M].北京:北京理工大学出版社,1995.
[13]	Huang W,Dietrich D L.An alternative degradation reliability modeling approach using maximum likelihood estimation[J].Transactions on Reliability,2005,54(2):310-317.
[14]	刘勇,倪平涛,尚永爽.基于HMM的开关电源故障预测方法研究[J].计算机测量与控制,2011,19(10):2367-2369. LIU Yong,NI Pingtao,SHANG Yongshuang.Research on failure prediction for switch power based on HMM[J].Computer Measurement and Control,2011,19(10):2367-2369.(in Chinese)
[15]	Hamada M S,Wilson A G,Reese C S,et al.Bayesian reliability[M].New York:Springer,2008.