Title: Uncertainty Management in Prognosis of Electrical Vehicle Energy System
Dr. Vachtsevanos, Advisor
Dr. Bennett, Chair
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.