A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells

Battery Management System (BMS) design for Lithium-ion batteries State of Charge (SoC) prediction has a crucial role in Electric Vehicles (EVs) and smart grids development. The need to design compact, light and fast devices requires finding a suitable trade-off between effectiveness and efficiency....

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Stefano Leonori, Luca Baldini, Antonello Rizzi, Fabio Massimo Frattale Mascioli
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	battery management system neural networks Li-ion battery ensemble neural network circuit equivalent models state of charge Technology T
Acceso en línea:	https://doaj.org/article/b0dae58256804a27a721f56ef5e45a5b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b0dae58256804a27a721f56ef5e45a5b
record_format	dspace
spelling	oai:doaj.org-article:b0dae58256804a27a721f56ef5e45a5b2021-11-11T16:05:58ZA Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells10.3390/en142173861996-1073https://doaj.org/article/b0dae58256804a27a721f56ef5e45a5b2021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7386https://doaj.org/toc/1996-1073Battery Management System (BMS) design for Lithium-ion batteries State of Charge (SoC) prediction has a crucial role in Electric Vehicles (EVs) and smart grids development. The need to design compact, light and fast devices requires finding a suitable trade-off between effectiveness and efficiency. In the literature, it is well emphasized that the application of electrochemical-based methods such as the Pseudo-Two-Dimensional (P2D) model is computationally prohibitive and requires significant simplifications. Conversely, plain Equivalent Circuit Models (ECM) are too simple and unable to represent the cell dynamics. The application of an Ensemble Neural Network (ENN) as Equivalent Neural Network Circuit (ENNC) emerged as a promising solution able to synthesize expressive and computationally efficient models. Indeed, with the support of a suitable dataset, an ENN can be configured to represent a given ECM, modeling each lumped parameter through an assigned Neural Network (NN). Accordingly, the ENNC system is able to keep a physical description of the battery cell while approximating the non-linear dynamic of each component. The paper proposes a novel ENNC battery named Physical Inspired-Equivalent Neural Network Circuit (PI-ENNC) whose ensemble architecture relies on a fractional-order Extended Single Particle (ESP) Lithium-ion cell formulation. The PI-ENNC is designed to approximate the ESP transfer functions referred to the ohmic effects, the electrolyte diffusion and the non-uniform charge distribution in the cell. The proposed model has been tested with three publicly available datasets, investigating the model behavior according to two different training strategies and with different input configurations. In order to prove its effectiveness, results have been compared with a simpler version proposed in a previous work. Results highlight the effectiveness of PI-ENNC in SoC prediction, underlining the importance of designing an ENN architecture that leverages on equations and constraints that reflect the physical phenomena of the cell.Stefano LeonoriLuca BaldiniAntonello RizziFabio Massimo Frattale MascioliMDPI AGarticlebattery management systemneural networksLi-ion batteryensemble neural networkcircuit equivalent modelsstate of chargeTechnologyTENEnergies, Vol 14, Iss 7386, p 7386 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	battery management system neural networks Li-ion battery ensemble neural network circuit equivalent models state of charge Technology T
spellingShingle	battery management system neural networks Li-ion battery ensemble neural network circuit equivalent models state of charge Technology T Stefano Leonori Luca Baldini Antonello Rizzi Fabio Massimo Frattale Mascioli A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells
description	Battery Management System (BMS) design for Lithium-ion batteries State of Charge (SoC) prediction has a crucial role in Electric Vehicles (EVs) and smart grids development. The need to design compact, light and fast devices requires finding a suitable trade-off between effectiveness and efficiency. In the literature, it is well emphasized that the application of electrochemical-based methods such as the Pseudo-Two-Dimensional (P2D) model is computationally prohibitive and requires significant simplifications. Conversely, plain Equivalent Circuit Models (ECM) are too simple and unable to represent the cell dynamics. The application of an Ensemble Neural Network (ENN) as Equivalent Neural Network Circuit (ENNC) emerged as a promising solution able to synthesize expressive and computationally efficient models. Indeed, with the support of a suitable dataset, an ENN can be configured to represent a given ECM, modeling each lumped parameter through an assigned Neural Network (NN). Accordingly, the ENNC system is able to keep a physical description of the battery cell while approximating the non-linear dynamic of each component. The paper proposes a novel ENNC battery named Physical Inspired-Equivalent Neural Network Circuit (PI-ENNC) whose ensemble architecture relies on a fractional-order Extended Single Particle (ESP) Lithium-ion cell formulation. The PI-ENNC is designed to approximate the ESP transfer functions referred to the ohmic effects, the electrolyte diffusion and the non-uniform charge distribution in the cell. The proposed model has been tested with three publicly available datasets, investigating the model behavior according to two different training strategies and with different input configurations. In order to prove its effectiveness, results have been compared with a simpler version proposed in a previous work. Results highlight the effectiveness of PI-ENNC in SoC prediction, underlining the importance of designing an ENN architecture that leverages on equations and constraints that reflect the physical phenomena of the cell.
format	article
author	Stefano Leonori Luca Baldini Antonello Rizzi Fabio Massimo Frattale Mascioli
author_facet	Stefano Leonori Luca Baldini Antonello Rizzi Fabio Massimo Frattale Mascioli
author_sort	Stefano Leonori
title	A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells
title_short	A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells
title_full	A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells
title_fullStr	A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells
title_full_unstemmed	A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells
title_sort	physically inspired equivalent neural network circuit model for soc estimation of electrochemical cells
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b0dae58256804a27a721f56ef5e45a5b
work_keys_str_mv	AT stefanoleonori aphysicallyinspiredequivalentneuralnetworkcircuitmodelforsocestimationofelectrochemicalcells AT lucabaldini aphysicallyinspiredequivalentneuralnetworkcircuitmodelforsocestimationofelectrochemicalcells AT antonellorizzi aphysicallyinspiredequivalentneuralnetworkcircuitmodelforsocestimationofelectrochemicalcells AT fabiomassimofrattalemascioli aphysicallyinspiredequivalentneuralnetworkcircuitmodelforsocestimationofelectrochemicalcells AT stefanoleonori physicallyinspiredequivalentneuralnetworkcircuitmodelforsocestimationofelectrochemicalcells AT lucabaldini physicallyinspiredequivalentneuralnetworkcircuitmodelforsocestimationofelectrochemicalcells AT antonellorizzi physicallyinspiredequivalentneuralnetworkcircuitmodelforsocestimationofelectrochemicalcells AT fabiomassimofrattalemascioli physicallyinspiredequivalentneuralnetworkcircuitmodelforsocestimationofelectrochemicalcells
_version_	1718432435227590656

A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells

Ejemplares similares