Machine Learning-Based State-of-Health Estimation of Battery Management Systems Using Experimental and Simulation Data

In pursuit of zero-emission targets, increasing sustainability concerns have prompted urban centers to adopt more environmentally friendly modes of transportation, notably through the deployment of electric vehicles (EVs). A prominent manifestation of this shift is the transition from conventional f...

Full description

Saved in:
Bibliographic Details
Main Authors: Anas Al-Rahamneh, Irene Izco, Adrian Serrano-Hernandez, Javier Faulin
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/14/2247
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849303514325450752
author Anas Al-Rahamneh
Irene Izco
Adrian Serrano-Hernandez
Javier Faulin
author_facet Anas Al-Rahamneh
Irene Izco
Adrian Serrano-Hernandez
Javier Faulin
author_sort Anas Al-Rahamneh
collection DOAJ
description In pursuit of zero-emission targets, increasing sustainability concerns have prompted urban centers to adopt more environmentally friendly modes of transportation, notably through the deployment of electric vehicles (EVs). A prominent manifestation of this shift is the transition from conventional fuel-powered buses to electric buses (e-buses), which, despite their environmental benefits, introduce significant operational challenges—chief among them, the management of battery systems, the most critical and complex component of e-buses. The development of efficient and reliable Battery Management Systems (BMSs) is thus central to ensuring battery longevity, operational safety, and overall vehicle performance. This study examines the potential of intelligent BMSs to improve battery health diagnostics, extend service life, and optimize system performance through the integration of simulation, real-time analytics, and advanced deep learning techniques. Particular emphasis is placed on the estimation of battery state of health (SoH), a key metric for predictive maintenance and operational planning. Two widely recognized deep learning models—Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM)—are evaluated for their efficacy in predicting SoH. These models are embedded within a unified framework that combines synthetic data generated by a physics-informed battery simulation model with empirical measurements obtained from real-world battery aging datasets. The proposed approach demonstrates a viable pathway for enhancing SoH prediction by leveraging both simulation-based data augmentation and deep learning. Experimental evaluations confirm the effectiveness of the framework in handling diverse data inputs, thereby supporting more robust and scalable battery management solutions for next-generation electric urban transportation systems.
format Article
id doaj-art-8e79d2b0a71e49e5924741b4f191b3f8
institution Kabale University
issn 2227-7390
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-8e79d2b0a71e49e5924741b4f191b3f82025-08-20T03:58:26ZengMDPI AGMathematics2227-73902025-07-011314224710.3390/math13142247Machine Learning-Based State-of-Health Estimation of Battery Management Systems Using Experimental and Simulation DataAnas Al-Rahamneh0Irene Izco1Adrian Serrano-Hernandez2Javier Faulin3Integrated Group of Logistics and Transportation-Operations Research (GILT-OR), Institute of Smart Cities, Public University of Navarre, 31006 Pamplona, SpainIntegrated Group of Logistics and Transportation-Operations Research (GILT-OR), Institute of Smart Cities, Public University of Navarre, 31006 Pamplona, SpainIntegrated Group of Logistics and Transportation-Operations Research (GILT-OR), Institute of Smart Cities, Public University of Navarre, 31006 Pamplona, SpainIntegrated Group of Logistics and Transportation-Operations Research (GILT-OR), Institute of Smart Cities, Public University of Navarre, 31006 Pamplona, SpainIn pursuit of zero-emission targets, increasing sustainability concerns have prompted urban centers to adopt more environmentally friendly modes of transportation, notably through the deployment of electric vehicles (EVs). A prominent manifestation of this shift is the transition from conventional fuel-powered buses to electric buses (e-buses), which, despite their environmental benefits, introduce significant operational challenges—chief among them, the management of battery systems, the most critical and complex component of e-buses. The development of efficient and reliable Battery Management Systems (BMSs) is thus central to ensuring battery longevity, operational safety, and overall vehicle performance. This study examines the potential of intelligent BMSs to improve battery health diagnostics, extend service life, and optimize system performance through the integration of simulation, real-time analytics, and advanced deep learning techniques. Particular emphasis is placed on the estimation of battery state of health (SoH), a key metric for predictive maintenance and operational planning. Two widely recognized deep learning models—Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM)—are evaluated for their efficacy in predicting SoH. These models are embedded within a unified framework that combines synthetic data generated by a physics-informed battery simulation model with empirical measurements obtained from real-world battery aging datasets. The proposed approach demonstrates a viable pathway for enhancing SoH prediction by leveraging both simulation-based data augmentation and deep learning. Experimental evaluations confirm the effectiveness of the framework in handling diverse data inputs, thereby supporting more robust and scalable battery management solutions for next-generation electric urban transportation systems.https://www.mdpi.com/2227-7390/13/14/2247machine learningdeep learningsimulationagent-based modelingbattery management systemstate of health estimation
spellingShingle Anas Al-Rahamneh
Irene Izco
Adrian Serrano-Hernandez
Javier Faulin
Machine Learning-Based State-of-Health Estimation of Battery Management Systems Using Experimental and Simulation Data
Mathematics
machine learning
deep learning
simulation
agent-based modeling
battery management system
state of health estimation
title Machine Learning-Based State-of-Health Estimation of Battery Management Systems Using Experimental and Simulation Data
title_full Machine Learning-Based State-of-Health Estimation of Battery Management Systems Using Experimental and Simulation Data
title_fullStr Machine Learning-Based State-of-Health Estimation of Battery Management Systems Using Experimental and Simulation Data
title_full_unstemmed Machine Learning-Based State-of-Health Estimation of Battery Management Systems Using Experimental and Simulation Data
title_short Machine Learning-Based State-of-Health Estimation of Battery Management Systems Using Experimental and Simulation Data
title_sort machine learning based state of health estimation of battery management systems using experimental and simulation data
topic machine learning
deep learning
simulation
agent-based modeling
battery management system
state of health estimation
url https://www.mdpi.com/2227-7390/13/14/2247
work_keys_str_mv AT anasalrahamneh machinelearningbasedstateofhealthestimationofbatterymanagementsystemsusingexperimentalandsimulationdata
AT ireneizco machinelearningbasedstateofhealthestimationofbatterymanagementsystemsusingexperimentalandsimulationdata
AT adrianserranohernandez machinelearningbasedstateofhealthestimationofbatterymanagementsystemsusingexperimentalandsimulationdata
AT javierfaulin machinelearningbasedstateofhealthestimationofbatterymanagementsystemsusingexperimentalandsimulationdata