(2012.9.11 TUE 10:00am S309)Prof.Ye Zhisheng:The Inverse Gaussian Process as a Degradation Model

  • lyshen@gucas.ac.cn
  • Created: 2012-09-07

Ye Zhisheng, research assistant professor, Hong Kong Polytechnique

Inviter: 胡庆培 助理研究员

The Inverse Gaussian Process as a Degradation Model

Time & Venue:
2012.9.11 TUE 10:00am S309(思源楼)

Degradation analysis has become a burgeoning research area in recent years to meet the requirement of complex systems. Previously, Wiener and Gamma process models have been extensively studied for degradation modelling. This paper systematically introduces the third class, i.e., the inverse Gaussian (IG) process, as an effective degradation model. The IG process is shown to be a limiting compound Poisson process, which gives it a meaningful physical interpretation for modelling degradation of products deteriorating in random environments. Treated as the first passage process of a Wiener process, the IG process is flexible in incorporating random effects and covariates that account for heterogeneities commonly observed in degradations. This flexibility makes the class of IG process models much more attractive compared with the Gamma process, which has been thoroughly investigated in the literature of degradation modelling. The paper also discusses the statistical inference of the three random effects models and their model selections. It concludes with a real world example to demonstrate the applicability of the IG process in degradation modelling.


Dr Ye Zhisheng obtained his PhD in Industrial & Systems Engineering from National University of Singapore, and his bachelor degrees in Material Science & Engineering and Economics, both from Tsinghua University. He is currently a researcher at the Management Science department in University of Strathclyde, UK, and will join the Applied Mathematics department in the Hong Kong Polytechnique University as a research assistant professor this September. His research interests include reliability modelling, reliability statistics, degradation analysis, and field failure data analysis. More information can be found from the website www.yezhisheng.com.