Modelling times between failures of a repairable system is of interest in many real world applications such as estimation of the number of warranty claims and scheduling maintenance policies and is the prerequisite of optimisation of maintenance policies is the knowledge. In practice, technical systems are composed of multiple components. Failure data collected from the field are normally masked in the sense that times between failures are available but the causes of failures are lacking. For the simplest example where a failed component in the system is replaced with a new identical one, the failure process of such a system forms a superimposed renewal process (SRP). For more complicating examples where a failed component is repaired, modelling the failure process of the system becomes very challenging. This presentation aims to review some recent developments in modelling the SRP and extend the discussion to the scenario when imperfect repair is conducted on failed components.
University of Kent, UK
Dr. Shaomin Wu is a professor of Business/Applied Statistics at the University of Kent, UK. He obtained his MSc and PhD degrees in applied statistics. His research interests include reliability mathematics, machine learning and survival data analysis, in which he has published papers in journals and conferences. Shaomin is an associate editor of IMA Journal of Management Mathematics, IISE Transactions, and Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability. He also serves as a member on the editorial boards of Reliability Engineering and System Safety, and International Journal of Reliability, Quality and Safety Engineering.