PhD in Computer Science

The development of electric vertical take-off and landing (eVTOL) vehicles is one of the best solutions for solving transportation problems such as air pollution, road congestion, and long commute times. Lithium-ion batteries due to their high energy density, long lifetime, fast charging, wide operating temperature, and light weight, are the most common choice for the energy storage system (ESS). On the other hand, fuel cells have been more popular in recent years, especially in transportation applications due to their high energy density and capability to operate in a wide temperature range. To have high energy and power densities at the same time in eVTOLs applications, using a hybrid energy storage system (HESS) consisting of lithium-ion batteries and fuel cells seems to be a feasible solution. An effective energy management system (EMS) is then necessary to monitor the states and optimize the use of HESS, consequently enhancing the eVTOL’s desired performance. The state-of-the-art review indicates the major research gaps for eVTOL’s EMS, including: 1-Inability of Rule-based EMS to guarantee optimal performance, 2- Violations with the constraints and missing safety in the optimization-based methods, 3- Weakness of the model-predictive-control (MPC) against HESS’s parameters uncertainties, noises, and disturbances, 4-Limited flight data for adaptive methods, and 5- Failure to use a robust state estimator to increase robustness of EMS in eVTOL, have not been filled by studies. To address these research gaps, this PhD project is developed answer two key research questions: 1- How to utilize robust and adaptive techniques to develop a resilient, scalable, and adaptable state estimator subject to different state estimation tasks in eVTOLs? 2- How can AI, MPC, and optimization be utilized to develop a resilient EMS that meets the development challenges of eVTOLs?