Battery state-of-charge estimator using the SVM technique

By J. Antón, P. J. García Nieto, Francisco Javier de Cos Juez, Fernando Sánchez Lasheras, M. G. Vega, M. R. Gutiérrez. 2013

178 citations recorded by the source corpus.

Abstract State-of-charge (SOC) is the equivalent of a fuel gauge for a battery pack in an electric vehicle. Determining the state-of-charge becomes an important issue in all battery applications including electric vehicles (EV), hybrid electric vehicles (HEV) or portable devices. The aim of this innovative study is to estimate the SOC of a high capacity lithium iron phosphate (LiFePO 4 ) battery cell from an experimental data-set obtained in the University of Oviedo Battery Laboratory (UOB Lab) using support vector machine (SVM) approach. The SOC of a battery cannot be measured directly and must be estimated from measurable battery parameters such as current, voltage or temperature. An accurate predictive model able to forecast the SOC in the short term is obtained. The agreement of the SVM model with the experimental data-set confirmed its good performance.

Subfields: Automotive Engineering, Control and Systems Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/d91f9d3945ad10ee53f63788f45e88fcbf3367cd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

1. Carlos Vidal
2. Pawel Malysz
3. P. Kollmeyer
4. Ali Emadi
5. Ryan M. Ahmed
6. Matthias Preindl
7. Ephrem Chemali

In Control and Systems Engineering

1. Ali Emadi
2. Carlos Vidal
3. Matthias Preindl
4. Ephrem Chemali
5. Pawel Malysz
6. P. Kollmeyer

In Electrical and Electronic Engineering

1. Carlos Vidal
2. Pawel Malysz
3. P. Kollmeyer
4. Ali Emadi
5. Ryan M. Ahmed
6. Matthias Preindl
7. Ephrem Chemali

Citations in the corpus

• Long Short-Term Memory Networks for Accurate State-of-Charge Estimation of Li-ion Batteries (2018, methodology): “In [17], [18], the authors used a SVM, however constant pulse discharge/charge profiles were mostly used in these works therefore the model’s ability to generalize to dynamic real world scenarios is unknown.”
• Machine Learning Applied to Electrified Vehicle Battery State of Charge and State of Health Estimation: State-of-the-Art (2020, methodology): “The most popular kernel is RBF, similar to equation (4); however, polynomial kernels are also possible [34].”