Date of Award
2016
Publication Type
Master Thesis
Degree Name
M.A.Sc.
Department
Electrical and Computer Engineering
Keywords
Electric Vehicles, Hybrid Energy Storage Systems
Supervisor
Kar, Narayan
Rights
info:eu-repo/semantics/openAccess
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Abstract
In electric vehicles, batteries are unable to entirely store the large amount of power from regenerative braking which is generated over a short time period. Batteries also have a lower efficiency when required to supply peaking power. Alternatively supercapacitors can handle peaking power at the expense of lower energy storage capacities. This is why hybrid energy storage systems using a battery and a supercapacitor are being researched. There exist multiple configurations and control strategies for these systems and recently some are beginning to take drive cycle data into consideration. The objective of this research is to design an intelligent algorithm for controlling the balancing of energy between a supercapacitor and a battery. By using machine learning methods, it’s able to learn from offline data where the optimal balancing can be calculated. The algorithm can then operate online, predicting how to balance the system which should improve the overall efficiency.
Recommended Citation
Lesiuta, Eric, "Optimization of a Hybrid Energy Storage System for Electric Vehicles Using Machine Learning Methods" (2016). Electronic Theses and Dissertations. 5837.
https://scholar.uwindsor.ca/etd/5837