Prognosis and diffusion process: a case study
IFAC Proceedings Volumes (IFAC-PapersOnline). 9th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, SAFEPROCESS 2015, Paris, 2-4 Sept. 2015
System monitoring and fault diagnosis generally requires the collection and analysis of working conditions and health indicators. Stochastic processes are suitable tools to model the system behavior by taking into account the dynamic evolution of collected data and the possible influencing random phenomenon. In this paper, a Markov-regime switching jump-di↵usion model is proposed for the health indicators modeling. The motivations behind the chosen model are highlighted and the model calibration method is presented. The proposed estimated process is able to reproduce real data characteristics and can be used for data forecasting and model-based decision making.