DocumentCode :
3250450
Title :
Reliability assessment based on proportional degradation hazards model
Author :
Chen, He-Tao ; Yuan, Hong-Jie
Author_Institution :
Sch. of Reliability & Syst. Eng., Beihang Univ., Beijing, China
fYear :
2010
fDate :
29-31 Oct. 2010
Firstpage :
958
Lastpage :
962
Abstract :
Proportional hazards model is introduced into dealing with accelerated degradation test data, and a model based on proportional degradation hazards model (PDHM) is proposed, the only assumption is that the logarithm of the degradation hazard function is a linear function of the stress covariates. The PDHM is established with degradation data, then the probability density function and Likelihood function of the model are derived, and maximum likelihood estimate (MLE) and Newton-Raphson method are utilized to estimate the model parameters. According to the relationship between failure threshold and degradation measure, the reliability model of the product is established, with which the reliability is assessed. The model in this paper is demonstrated correct and valid by assessing the reliability of percent increase in resistance over time of carbon-film resistors.
Keywords :
Newton-Raphson method; circuit reliability; circuit testing; electric resistance; electronics industry; maximum likelihood estimation; probability; resistors; Newton-Raphson method; accelerated degradation test data; carbon-film resistors; degradation hazard function; likelihood function; maximum likelihood estimate; probability density function; proportional degradation hazard model; reliability assessment; resistance; stress covariate; Analytical models; Brain modeling; Data models; Degradation; Life estimation; Reliability; Resistance; Degradation data; Newton-Raphson method; proportional degradation hazards model; reliability assessment;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Engineering and Engineering Management (IE&EM), 2010 IEEE 17Th International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4244-6483-8
Type :
conf
DOI :
10.1109/ICIEEM.2010.5646465
Filename :
5646465
Link To Document :
بازگشت