Title: ANN-based RBF prediction for maximal energy recovery using hybrid optimisation in electric vehicles

Authors: A. Velu; N. Chellammal

Addresses: Department of Electrical and Electronics Engineering, SRM Institute of Science and Technology, Kattankulathur, Chennai, 603203, Tamilnadu, India ' Department of Electrical and Electronics Engineering, SRM Institute of Science and Technology, Kattankulathur, Chennai, 603203, Tamilnadu, India

Abstract: Due to the increasing number of electric vehicles (EVs) that have propelled the global trend towards transportation electrification over the past few decades, the automotive industry has expanded its investment in transportation electrification technology. However, the widespread maintenance of EVs is significantly complicated by their short driving range. Therefore, a lot of research is done to improve the efficiency and driving range of automobiles in both business and academia. The operational range of EVs can be expanded using regenerative braking technology. Initially, the parameters, like speed of the EV and state of charge (SOC) of the battery are taken as input to the artificial neural network (ANN) and the corresponding predicted regenerative braking force has been obtained as the desired outcome of ANN. The estimated accuracy of the ANN classifier is then enhanced by optimally altering its weight parameters by Wild Horse Insisted Sparrow Search Optimisation (WHI-SSO).

Keywords: regenerative braking force; EV; energy recovery; ANN; artificial neural network; optimisation.

DOI: 10.1504/IJHVS.2025.147061

International Journal of Heavy Vehicle Systems, 2025 Vol.32 No.3, pp.416 - 437

Received: 21 Sep 2023
Accepted: 06 Jun 2024
Published online: 10 Jul 2025 *

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