作者：黄运来1, 张国龙2, 邓陈1, 柏航1
作者单位：1. 63981部队, 湖北 武汉 430311;
2. 军械工程学院光学与电子工程系, 河北 石家庄 050003
关键词：可靠性评估; 加速退化试验; ARMA模型; 时间序列
摘要：
有限时间内很难获得大量电子产品的失效数据,传统可靠性评估方法存在一定局限。在分析传统加速退化试验可靠性评估的基础之上,提出利用时间序列对产品加速退化过程描述的方法,使用自回归滑动平均混合(ARMA)模型对退化数据进行建模,通过参数估计得到其退化规律的表达式,从而外推出其失效寿命,进而利用极大似然估计理论进行可靠性评估。最后以某电源电路板加速退化试验数据为例,分时间序列建模和可靠性评估两大步骤,分别对95℃、105℃、115℃下加速退化试验数据进行分析处理,得出可靠性评估结果,验证该方法的有效性和实用性。
Accelerated degradation test reliability evaluation based on ARMA model
HUANG Yun-lai1, ZHANG Guo-long2, DENG Chen1, BAI Hang1
1. Unit 63981, Wuhan 430311, China;
2. Optical and Electronic Engineering Department of Ordnance Engineering College, Shijiazhuang 050003, China
Abstract: As it is difficult to obtain the failure data of electronic products in limited time, the traditional methods of reliability evaluation are limited. On the basis of analysis on traditional accelerated degradation test reliability evaluation, the use of time series of accelerated degradation method of process description was proposed. Using degradation data to build the auto-regressive and moving average (ARMA) model and using parameter estimation to get expression degradation law. The failure life was launched from the outside and reliability evaluation was estimated using maximum likelihood theory. Finally, to verify the effectiveness and practicability of the method, power supply circuit board accelerated degradation test data were used as an example. Two steps of time series modeling and reliability evaluation are clarified and accelerated degradation test data at 95,105 and 115℃ were analyzed.
Keywords: reliability evaluation; accelerated degradation test; auto-regressive and moving average model; time series
2014, 40(4): 137-140 收稿日期: 2013-6-25;收到修改稿日期: 2013-8-20
基金项目: 国家自然科学基金项目(61271153)
作者简介: 黄运来(1985-),男,湖南邵阳市人,工程师,硕士,研究方向为装备计量及系统性能测试。
参考文献
[1] LU C J, Meeker W Q. Using degradation measures to estimate a time-to-failure distribution[J]. Technometrics, 1993,35(2):161-174.
[2] 马强,钟强晖,张志华. 基于时间序列的退化型产品可靠性评估方法[J]. 襄樊学院学报,2011,32(2):19-23.
[3] 尤琦,赵宇,胡广平. 基于时序模型的加速退化数据可靠性评估[J]. 系统工程理论与实践,2011,31(2):328-332.
[4] 邓爱民,陈循,张春华. 基于加速退化数据的可靠性评估[J].弹箭与制导学报,2006,26(2):808-815.
[5] 陶庄,金水高. 时间序列分析简明攻略[J]. 中国卫生统计,2003(3):151-153.
[6] Meeker W Q, Escobar L A, Lu J C. Accelerated degradation tests:modeling and analysis[J]. Technometrics,1998,40(2):89-99.
[7] 魏武雄. 时间序列分析:单变量和多变量方法[M]. 北京:中国人民大学出版社,2005.
[8] 王玉明. 基于性能退化数据的电子产品可靠性分析研究[D].石家庄:军械工程学院,2008.
