FPGA Implementation of an Ant Colony Optimization Based SVM Algorithm for State of Charge Estimation in Li-Ion Batteries

Monitoring the State of Charge (SoC) in battery cells is necessary to avoid damage and to extend battery life. Support Vector Machine (SVM) algorithms and Machine Learning techniques in general can provide real-time SoC estimation without the need to design a cell model. In this work, an SVM was tra...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mattia Stighezza, Valentina Bianchi, Ilaria De Munari
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	state-of-charge (SoC) estimation battery management FPGA VHDL ant colony optimization (ACO) Technology T
Acceso en línea:	https://doaj.org/article/dc8a7dd11e304814afa768f60fc83230
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dc8a7dd11e304814afa768f60fc83230
record_format	dspace
spelling	oai:doaj.org-article:dc8a7dd11e304814afa768f60fc832302021-11-11T15:52:16ZFPGA Implementation of an Ant Colony Optimization Based SVM Algorithm for State of Charge Estimation in Li-Ion Batteries10.3390/en142170641996-1073https://doaj.org/article/dc8a7dd11e304814afa768f60fc832302021-10-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7064https://doaj.org/toc/1996-1073Monitoring the State of Charge (SoC) in battery cells is necessary to avoid damage and to extend battery life. Support Vector Machine (SVM) algorithms and Machine Learning techniques in general can provide real-time SoC estimation without the need to design a cell model. In this work, an SVM was trained by applying an Ant Colony Optimization method. The obtained trained model was 10-fold cross-validated and then designed in Hardware Description Language to be run on FPGA devices, enabling the design of low-cost and compact hardware. Thanks to the choice of a linear SVM kernel, the implemented architecture resulted in low resource usage (about 1.4% of Xilinx Artix7 XC7A100TFPGAG324C FPGA), allowing multiple instances of the SVM SoC estimator model to monitor multiple battery cells or modules, if needed. The ability of the model to maintain its good performance was further verified when applied to a dataset acquired from different driving cycles to the cycle used in the training phase, achieving a Root Mean Square Error of about 1.4%.Mattia StighezzaValentina BianchiIlaria De MunariMDPI AGarticlestate-of-charge (SoC) estimationbattery managementFPGAVHDLant colony optimization (ACO)TechnologyTENEnergies, Vol 14, Iss 7064, p 7064 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	state-of-charge (SoC) estimation battery management FPGA VHDL ant colony optimization (ACO) Technology T
spellingShingle	state-of-charge (SoC) estimation battery management FPGA VHDL ant colony optimization (ACO) Technology T Mattia Stighezza Valentina Bianchi Ilaria De Munari FPGA Implementation of an Ant Colony Optimization Based SVM Algorithm for State of Charge Estimation in Li-Ion Batteries
description	Monitoring the State of Charge (SoC) in battery cells is necessary to avoid damage and to extend battery life. Support Vector Machine (SVM) algorithms and Machine Learning techniques in general can provide real-time SoC estimation without the need to design a cell model. In this work, an SVM was trained by applying an Ant Colony Optimization method. The obtained trained model was 10-fold cross-validated and then designed in Hardware Description Language to be run on FPGA devices, enabling the design of low-cost and compact hardware. Thanks to the choice of a linear SVM kernel, the implemented architecture resulted in low resource usage (about 1.4% of Xilinx Artix7 XC7A100TFPGAG324C FPGA), allowing multiple instances of the SVM SoC estimator model to monitor multiple battery cells or modules, if needed. The ability of the model to maintain its good performance was further verified when applied to a dataset acquired from different driving cycles to the cycle used in the training phase, achieving a Root Mean Square Error of about 1.4%.
format	article
author	Mattia Stighezza Valentina Bianchi Ilaria De Munari
author_facet	Mattia Stighezza Valentina Bianchi Ilaria De Munari
author_sort	Mattia Stighezza
title	FPGA Implementation of an Ant Colony Optimization Based SVM Algorithm for State of Charge Estimation in Li-Ion Batteries
title_short	FPGA Implementation of an Ant Colony Optimization Based SVM Algorithm for State of Charge Estimation in Li-Ion Batteries
title_full	FPGA Implementation of an Ant Colony Optimization Based SVM Algorithm for State of Charge Estimation in Li-Ion Batteries
title_fullStr	FPGA Implementation of an Ant Colony Optimization Based SVM Algorithm for State of Charge Estimation in Li-Ion Batteries
title_full_unstemmed	FPGA Implementation of an Ant Colony Optimization Based SVM Algorithm for State of Charge Estimation in Li-Ion Batteries
title_sort	fpga implementation of an ant colony optimization based svm algorithm for state of charge estimation in li-ion batteries
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/dc8a7dd11e304814afa768f60fc83230
work_keys_str_mv	AT mattiastighezza fpgaimplementationofanantcolonyoptimizationbasedsvmalgorithmforstateofchargeestimationinliionbatteries AT valentinabianchi fpgaimplementationofanantcolonyoptimizationbasedsvmalgorithmforstateofchargeestimationinliionbatteries AT ilariademunari fpgaimplementationofanantcolonyoptimizationbasedsvmalgorithmforstateofchargeestimationinliionbatteries
_version_	1718433147262074880

FPGA Implementation of an Ant Colony Optimization Based SVM Algorithm for State of Charge Estimation in Li-Ion Batteries

Ejemplares similares