Abhijit Kulkarni, Remus Teodorescu
A key function of battery management systems (BMS) in e-mobility applications is estimating the battery state of health (SoH) with high accuracy. This is typically achieved in commercial BMS using model-based methods. This paper proposes a computationally efficient and data-lightweight SoH estimation technique that employs online impedance at four discrete frequencies to derive features for a linear regression approach. The proposed solution circumvents the complexities associated with traditional AI/ML methods that are often unsuitable for low-cost microcontrollers in BMS due to demanding non-linear functions and matrix operations. The accuracy of this method is validated using two experimental datasets, demonstrating a mean absolute error (MAE) of less than 2% across diverse training and testing examples. The findings underscore the method's effectiveness and practicality, making it suitable for real-time implementation in commercial BMS applications.
@article{295d099e-7d09-4eb4-a344-2fef94fc88af,
title={Computationally Efficient Machine-Learning-Based Online Battery State of Health Estimation},
author={Abhijit Kulkarni and Remus Teodorescu},
year={2023},
language={en}
}TY - JOUR TI - Computationally Efficient Machine-Learning-Based Online Battery State of Health Estimation AU - Abhijit Kulkarni AU - Remus Teodorescu PY - 2023 LA - en ER -
Rajesh Jha, Bimal Kumar Jha
This book describes the application of artificial intelligence (AI) and machine learning (ML) concepts to develop predictive models that can be used t
Roger Rumbu
"Powering in Progress: A Comprehensive Guide to Battery Technology" is a journey into the heart of this dynamic and indispensable energy storage pheno
This paper addresses the challenge of assessing the feasibility of wind power plant projects at sites with insufficient or no local historic wind data
Important advances in electrochemical engineering technology over the last three decades have fostered the development of a lternative methods to alle