The 8th International Conference on System Reliability and Safety
Sicily, Italy - November 20-22, 2024

Fabio Postiglione, University of Salerno, Italy

 

Fabio Postiglione is an Associate Professor of Statistics at the University of Salerno, Italy. He received his “Laurea” degree (5 years, summa cum laude) in Electronics Engineering and his Ph.D. degree in Information Engineering from University of Salerno, Italy. He was a Research Fellow at the University of Sannio, on topics related to gravitational waves data analysis, and worked as a Research Engineer in the Tin.it R&D department (Telecom Italia Group). His research interests include Bayesian methods, statistical characterization of degradation processes and lifetime estimation, and reliability and availability modeling of complex systems (e.g., telecommunication networks, fuel cells). Prof. Postiglione is a member of the Italian Statistical Society (SIS), of the Italian National Inter-University Consortium for Telecommunications (CNIT), of the European Network for Business and Industrial Statistics (ENBIS), and a past member of LIGO, VIRGO, KAGRA collaborations for the detection of gravitational waves and of the Italian National Institute of Nuclear Physics (INFN). He is/has been involved in many European and Italian research projects. He has co-authored more than 130 papers, published in international journals and conference proceedings, and one international patent.

Speech Title: Bayesian approaches for bounded transformed gamma processes
 
Abstract: The bounded transformed gamma process has been recently introduced to describe degradation processes of technological systems, where the degradation level can not exceed a given upper limit, due to inherent characteristics of the system or of the degradation mechanism itself. Some Bayesian approaches for this stochastic process are presented. A Bayesian inferential procedure is developed to the aim of incorporating different levels of prior information the analyst might possess on the upper limit and on other physical characteristics of the degradation phenomenon under observation. Also a Bayesian model selection method, based on the Bayes factor, is introduced to select the functional form of one of the key functions ruling the process, the bounded state function, among suitable alternatives. The proposed procedures are implemented by adopting some Markov Chain Monte Carlo techniques and are validated on a set of real data consisting of the wear measurements, in different time instants, of the liners of an 8-cylinder Diesel engine for marine propulsion.