Physics-informed neural networks for voltage and SOC estimation

Andrew Forde

Physics-informed neural networks for voltage and SOC estimation

Andrew Forde

School of Mechanical and Aerospace Engineering

Research output: Contribution to conference › Poster

6 Downloads (Pure)

Abstract

This work shows benefits of applying simple physics-informed methods to neural networks for battery electrical response prediction

Original language	English
Publication status	Published - 13 Jun 2022
Event	Advanced Automotive Battery Conference 2022 - Germany (Attended online), Mainz, Germany Duration: 13 Jun 2022 → 15 Jun 2022

Conference

Conference	Advanced Automotive Battery Conference 2022
Abbreviated title	AABC 2022
Country/Territory	Germany
City	Mainz
Period	13/06/2022 → 15/06/2022

Keywords

machine learning
battery
battery management system
lithium-ion batteries
electric vehicle

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

Physics-informed neural networks for voltage and SOC estimation
Copyright 2022 the author.
Other version, 318 KBLicence: Unspecified

Physics-informed neural networks for battery response prediction
Forde, A. (Author), Nockemann, P. (Supervisor) & Glover, S. (Supervisor), Dec 2025
Student thesis: Doctoral Thesis › Doctor of Philosophy

File

Cite this

@conference{8ef6a977f987402cba5f6c25ca0b00c5,

title = "Physics-informed neural networks for voltage and SOC estimation",

abstract = "This work shows benefits of applying simple physics-informed methods to neural networks for battery electrical response prediction",

keywords = "machine learning, battery, battery management system, lithium-ion batteries, electric vehicle",

author = "Andrew Forde",

year = "2022",

month = jun,

day = "13",

language = "English",

note = "Advanced Automotive Battery Conference 2022, AABC 2022 ; Conference date: 13-06-2022 Through 15-06-2022",

}

TY - CONF

T1 - Physics-informed neural networks for voltage and SOC estimation

AU - Forde, Andrew

PY - 2022/6/13

Y1 - 2022/6/13

N2 - This work shows benefits of applying simple physics-informed methods to neural networks for battery electrical response prediction

AB - This work shows benefits of applying simple physics-informed methods to neural networks for battery electrical response prediction

KW - machine learning

KW - battery

KW - battery management system

KW - lithium-ion batteries

KW - electric vehicle

M3 - Poster

T2 - Advanced Automotive Battery Conference 2022

Y2 - 13 June 2022 through 15 June 2022

ER -

Physics-informed neural networks for voltage and SOC estimation

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Student theses

Physics-informed neural networks for battery response prediction

Cite this