Title: Battery state of charge and driving range estimation for electric bus based on vehicular network information

Authors: Xinxin Zhao; Shuangzhe Xu; Haoran Lei; Bing Li

Addresses: School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, 100083, China ' School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, 100083, China ' School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, 100083, China ' School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, 100083, China

Abstract: Battery state of charge and driving range are important vehicle data in the battery management system of electric vehicles. It reduces driver mileage anxiety and helps the driver to arrange the subsequent trips of the vehicle properly if they are accurately predicted. In this paper, the data are processed to extract the operating characteristics related to the energy consumption characteristics of the vehicle based on vehicle data provided by Beijing's pure electric bus vehicle networking platform. We employed relevance vector machine (RVM) method to predict, and the battery charge state and vehicle range are successfully predicted by a particle swarm optimised multi-kernel RVM. The MAE and RMSE values of the prediction results are also in a range of small values.

Keywords: SOC estimation; driving range estimation; relevance vector machine; RVM; particle swarm optimisation; PSO.

DOI: 10.1504/IJEHV.2023.136767

International Journal of Electric and Hybrid Vehicles, 2023 Vol.15 No.4, pp.335 - 351

Received: 04 Jan 2023
Accepted: 01 Apr 2023
Published online: 21 Feb 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article