Estimation of electric vehicle turning radius through machine learning for roundabout cornering

No default citation style available for Eprints

Preview	Pdf Estimation of electric vehicle turning radius through machine learning .pdf Download (139kB) | Preview
	Pdf Estimation of electric vehicle turning radius through machine learning_FULL.pdf Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

This paper presents an alternative approach for estimating the turning radius using machine learning technique. While on-board sensors are unable to offer adequate information on vehicle states to the algorithm, vehicle states other than those directly detected by on-board sensors can be inferred using machine learning (ML) approaches based on the collected data. A compact electric vehicle model is used to obtain data and measurements of the vehicle states for different sets of road radius. The augmented basic measurements is fed to an Extra Tree Regression to predict the turning radius of the vehicle. The feasibility of the developed algorithm was tested and validated using performance metrics. The results show that the regression accuracy for the turning radius is 99% and can be obtained with sufficient vehicle dynamics information.

Item Type:	Conference or Workshop Item (Lecture)
Additional Information:	Indexed by Scopus
Uncontrolled Keywords:	Predictive modelling; Electric vehicle; Machine learning
Subjects:	T Technology > TJ Mechanical engineering and machinery T Technology > TK Electrical engineering. Electronics Nuclear engineering T Technology > TL Motor vehicles. Aeronautics. Astronautics
Faculty/Division:	Institute of Postgraduate Studies College of Engineering Faculty of Computing Faculty of Manufacturing and Mechatronic Engineering Technology Faculty of Mechanical and Automotive Engineering Technology
Depositing User:	Mrs Norsaini Abdul Samat
Date Deposited:	15 Aug 2022 01:30
Last Modified:	15 Aug 2022 01:30
URI:	http://umpir.ump.edu.my/id/eprint/34918
Download Statistic:	View Download Statistics

Actions (login required)

View Item