Abstract
The regeneration factor, that expresses the ratio between the energy recovered to the battery during braking and the total braking energy, is difficult to be measured from independent instruments. In this paper, a reinforcement learning (RL) method is used to adjust and improve a fuzzy logic model for regenerative braking (FLmRB) for modeling Electric Vehicles’ (EV) regenerative braking systems (RBSs). With the proposed approach, a specialist can infer the regeneration factor, by tuning the model for a specific EV using real data gathered from field tests, using as inputs, only variables measured from independent instruments, namely EV acceleration and jerk, and road inclination. The proposed approach was tested with real data sets of the Nissan Leaf EV. Twelve short-distance data sets in urban areas were collected to learn the regeneration factor, and two long-distance data sets in urban and sub-urban areas were used to validate the learned models. The results show that the learning method can successfully learn the regenerative braking factor improving the previously proposed FLmRB model approach which is based on manual design of the model.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Engineering Applications of Artificial Intelligence
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.