Title:  Uncertainty Management in Prognosis of Electrical Vehicle Energy System

Committee: 

Dr. Vachtsevanos, Advisor    

Dr. Bennett, Chair

Dr. Vela

Abstract:

The objective of the proposed research is to understand uncertainties inherent in engineering system prognosis (especially, electric vehicle energy system, as the testbed for the proposed research) and to shrink/contain uncertainty distribution bounds under long-term and usage-based prognosis. The enabling technologies build on a three-tier architecture: uncertainty representation, uncertainty propagation, and uncertainty management. These steps are addressed via a thorough analysis of prognosis methods, an uncertainty tree, sensitive analysis, inner-outer / hyper-parameter feedback loops for uncertainty management. The results of the proposed study will provide a database of uncertainty sources to the system, deriving more precise and accurate estimates of the remaining useful life or the end of life prediction, and assist to arrive at a true assessment of the current health state of complex engineering systems.