NOVA MATH – UNIDEMI Talks
Date | Time: October 11, 2023 | 14h00 – 15h00
Location: Building VII, Seminar room (2nd floor)
14:00 – 14:15
Duarte Dinis, Department of Mechanical and Industrial Engineering, UNIDEMI
Modeling uncertainty: An integrated forecasting and simulation methodology for maintenance capacity
Abstract: Despite the extensive amount of data generated and stored during the maintenance capacity planning process, Maintenance, Repair, and Overhaul (MRO) organizations have yet to explore the full potential of such data to deal with the uncertainty of decision-making, particularly in forecasting the required capacity to face future and unprecedented maintenance events. This presentation showcases an integrated forecasting and simulation methodology, used as a predictive analytics tool for maintenance capacity planning, and proposes challenges for the future.
14:15 – 14:30
Pedro Mota, Department of Mathematics, NOVA MATH
Diffusions with self-induced regime changes
Abstract: In this talk we present the formulation of self-induced regime switching diffusion models, with the regime switching defined by a change in the diffusion’s drift and/or volatility function and where the regime change occurs whenever the process trajectory crosses a threshold, possibly with some delay. The difference between the regimes can simply be given by different sets of real valued parameters, for the drift and diffusion functions, but can also be defined by allowing the underlying diffusion process to change from one family of diffusions in one regime to an entirely different one in the other regime. We will present some examples of self-induced regime switching models and estimation procedures.
14:30 – 15:00
Discussion