A Generalized Wiener Process Degradation Model with Two Transformed Time Scales

作者：Wang, Zhihua; Li, Junxing; Ma, Xiaobing^*; Zhang, Yongbo; Fu, Huimin; Krishnaswamy, Sridhar

来源：Quality and Reliability Engineering International, 2017, 33(4): 693-708.

DOI：10.1002/qre.2049

• performance degradation
• measurement error
• Wiener process model
• transformed time scale
• one-stage parameter estimation

Degradation analysis is very useful in reliability assessment for complex systems and highly reliable products, because few or even no failures are expected in a reasonable life test span for them. In order to further our study on degradation analysis, a novel Wiener process degradation model subject to measurement errors is proposed. Two transformed time scales are involved to depict the statistical property evolution over time. A situation where one transformed time scale illustrates a linear form for the degradation trend and the other transformed time scale shows a generalized quadratic form for the degradation variance is discussed particularly. A one-stage maximum likelihood estimation of parameters is constructed. The statistical inferences of this model are further discussed. The proposed method is illustrated and verified in a comprehensive simulation study and two real applications for indium tin oxide (ITO) conductive film and light emitting diode ( LED). The Wiener process model with mixed effects is considered as a reference. Comparisons show that the proposed method is more general and flexible, and can provide reasonable results, even in considerably small sample size circumstance.

• 出版日期2017-6
• 单位北京航空航天大学; 西北大学