Reliability evaluation using products' performance degradation data has become an important method which solves the problem of insufficient failure lifetime observations. On the basis of analyzing the close correlation between products' failure rate and failure critical values, the proportional failure rate mode was introduced for describing the relationship between products' life and failure critical values, and the degradation analysis model was built using the relationship between the lifetime distribution and the degradation characteristic' distribution. In the proposed approach, the physical degradation path model and the degradation characteristic's distribution were not assumed, the values of reliability at different inspection times and different failure critical values were got using products' degradation information, then the unknown parameters were estimated through distribution fitting method and reliability assessment was performed. This approach not only relaxes model assumptions, but applies to dealing with some non-balanced-structure degradation data, which makes it have better adaptability. Finally, an example was given to demonstrate the validity of this approach.
Meeker W Q,Escobar L A��Statistical methods for reliability data[M]��New York:John Wiley & Sons,INC,1998
Lu J C,Meeker W Q��Using degradation measures to estimate a time-to failure distribution[J]��1993,35(2):161-174
Crk V��Reliability assessment from degradation data //IEEE,Proceedings Annual Reliability and Maintainability Symposium.Los Angeles,CA,USA:IEEE,2000:155-161
ׯ����.�˻�ʧЧģ�ͼ���ͳ�Ʒ��� ���Ϻ�:����ʦ����ѧͳ��ϵ,1994 Zhuang Dongchen.Degradation failure model and its statistical analysis ��Shanghai:Statistics Department,East China Normal University,1994(in Chinese)
Yang K,Xue J��Continuous state reliability analysis //Proceedings Annual Reliability and Maintainability Symposium.Piscataway:IEEE,1996:251-257
Jayaram J S R,Girish T��Reliability prediction through degradation data modeling using a quasi-likelihood approach //Proceedings Annual Reliability and Maintainability Symposium.Piscataway:IEEE,2005:193-199
����ǿ,�뾲,��粣�����Poisson-Normal���������˻�ģ�͵Ŀɿ��Է���[J]��ϵͳ���������ѧ��,2006,28(11):1775-1778 Zhang Yongqiang,Feng Jing,Liu Qi��Reliability analysis based on performance degradation model of compound poisson-normal process[J]��Systems Engineering and Electronics,2006,28(11):1775-1778(in Chinese)