ICMAME 2023 Conference Proceedings

Paper No: 189
Paper Title: Personalization of AI-based Distance To Empty prediction model

Kihyung Joo Hyundai Motor Company, Seoul, South Korea
Lina Kim Hyundai Motor Company, Seoul, South Korea

It is an important factor in electric vehicles to show customers how much they can drive with the energy of the remaining battery. If the remaining mileage is not accurate, electric vehicle drivers will have no choice but have to feel anxious about the mileage. If the remaining mileage to drive is wrong, drivers may not be able to get to the charging station and may not be able to drive because the battery runs out. This study proposes a more advanced model by predicting the remaining mileage based on actual driving data and based on reflecting the pattern of customers who drive regularly. The basic model is a linear regression model, and the advanced model is a Bayesian linear regression model. In order to improve performance, the driver's regular driving pattern is recognized in advance before driving and it is reflected in the remaining driving mileage model. The actual driving log is used for the dataset. It can be seen that the performance of the model in this study is improved 10% better compared to the existing remaining driving mileage.

Keywords: Proportional Integral Derivative (PID), Swarm Intelligence (SI), Renewable Energy (RE), Statistical Analysis

Conference Venue: Mövenpick Hotel & Apartments Bur Dubai, Dubai-UAE
Conference Date: 29-30 April 2023

ISBN Number: 978-625-00-1526-1
DOI Number:

PDF Download

Flag Counter