Title: IoT and artificial intelligence enabled state of charge estimation for battery management system in hybrid electric vehicles

Authors: Siripuri Kiran; Niranjan Polala; M.S.B. Phridviraj; S. Venkatramulu; Chintakindi Srinivas; V. Chandra Shekhar Rao

Addresses: Department of CSE, Kakatiya Institute of Technology and Science, Warangal – 506015, Telagangana, India ' Department of CSE, Kakatiya Institute of Technology and Science, Warangal – 506015, Telagangana, India ' Department of CSE, Kakatiya Institute of Technology and Science, Warangal – 506015, Telagangana, India ' Department of CSE, Kakatiya Institute of Technology and Science, Warangal – 506015, Telagangana, India ' Department of CSE, Kakatiya Institute of Technology and Science, Warangal – 506015, Telagangana, India ' Department of CSE, Kakatiya Institute of Technology and Science, Warangal – 506015, Telagangana, India

Abstract: In recent times, Internet of Things (IoT) technologies have gained significant attention for the improvements and design of smart grids. The utilisation of hybrid electric vehicles (HEVs) as dynamic electrical energy management systems in smart grid possesses several benefits while affecting the grid and HEV battery pack. Amongst several HEV technologies, an effective battery management system (BMS) remains a challenging problem, which is mainly utilised to indicate the battery state of charge (SOC). The presented model involves a black widow optimisation (BWO) - based deep long short term (LSTM) based Stacked Autoencoder (LSTM-SAE). The utilisation of LSTMSAE model makes the modelling process easier and offers precise depiction of the input-output relationship of the battery model. The IoTAI-SOC model has reported superior results with the lower SOC error of [-2.1+3.2] and minimum SOC error of [-3.5+4.3] for 25°C temperature over the other existing methods in terms of different aspects.

Keywords: battery management; HEVs; hybrid electric vehicles; parameter tuning; deep learning; SOC; state of charge; artificial intelligence.

DOI: 10.1504/IJHVS.2022.128916

International Journal of Heavy Vehicle Systems, 2022 Vol.29 No.5, pp.463 - 479

Received: 25 Apr 2021
Accepted: 01 Jul 2021
Published online: 10 Feb 2023 *

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