A Review of the Applications of Explainable Machine Learning for Lithium–Ion Batteries: From Production to State and Performance Estimation

Aug 5, 2026

Upload by Finn

Lithium–ion batteries underpin clean transportation and emerging electrified mobility, including EVs, aircraft, and electric micromobilities. Battery cell design and manufacturing are inseparable from characterisation, monitoring, and control to improve energy delivery and industrial sustainability. Data-driven methods, especially artificial intelligence and machine learning, have accelerated progress across these stages. This review focuses on explainable machine learning (XML) for lithium–ion batteries, covering manufacturing and production optimization, and—during operation—state estimation and control for health, charge, and energy monitoring. It synthesizes theoretical techniques, discusses case studies, highlights research gaps, and proposes future directions to support adoption of XML toward a NetZero future.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages38

Reading Time1 h 36 min

AccessFree to download

Introduction

Background on Lithium–Ion Batteries and Data-Driven ML

Explainable Machine Learning for Battery Manufacturing

State and Performance Estimation with XML

energies Review A Review of the Applications of Explainable Machine Learning for Lithium–Ion Batteries: From Production to State and Performance Estimation Mona Faraji Niri 1,2, *, Koorosh Aslansefat 3, Sajedeh Haghi 4, Mojgan Hashemian 5, Rüdiger Daub 4 and James Marco 1,2 Citation: Faraji Niri, M.; Aslansefat, K.; Haghi, S.; Hashemian, M.; Daub, R.; Marco, J. A Review of the Applications of Explainable Machine Learning for Lithium–Ion Batteries: From Production to State and Performance Estimation. Energies 2023, 16, 6360. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.3390/en16176360](10.3390/en16176360) Academic Editor: Daniel-Ioan Stroe Received: 4 August 2023 Revised: 29 August 2023 Accepted: 30 August 2023 Published: 1 September 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 WMG, University of Warwick, Coventry CV4 7AL, UK;[james.marco@warwick.ac.uk](james.marco@warwick.ac.uk) 2 The Faraday Institution, Quad One, Harwell Science and Innovation Campus, Didcot OX11 0DG, UK 3 School of Computer Science, University of Hull, Hull HU6 7RX, UK; [k.aslansefat@hull.ac.uk](k.aslansefat@hull.ac.uk) 4 Institute for Machine Tools and Industrial Management, Technical University of Munich, Garching, Boltzmannstr. 15, 85748 Munich , Germany; sajedeh.haghi@iwb.tum.de (S.H.); [ruediger.daub@iwb.tum.de](ruediger.daub@iwb.tum.de) (R.D.) 5 Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal; [mojgan.hashemian@tecnico.ulisboa.pt](mojgan.hashemian@tecnico.ulisboa.pt) * [Correspondence: mona.faraji-niri@warwick.ac.uk](Correspondence: mona.faraji-niri@warwick.ac.uk) Abstract: Lithium–ion batteries play a crucial role in clean transportation systems including EVs, aircraft, and electric micromobilities. The design of battery cells and their production process are as important as their characterisation, monitoring, and control techniques for improved energy delivery and sustainability of the industry. In recent decades, the data-driven approaches for addressing all mentioned aspects have developed massively with promising outcomes, especially through artiﬁcial intelligence and machine learning. This paper addresses the latest developments in explainable machine learning known as XML and its application to lithium–ion batteries. It includes a critical review of the XML in the manufacturing and production phase, and then later, when the battery is in use, for its state estimation and control. The former focuses on the XML for optimising the battery structure, characteristics, and manufacturing processes, while the latter considers the monitoring aspect related to the states of health, charge, and energy. This paper, through a comprehensive review of theoretical aspects of available techniques and discussing various case studies, is an attempt to inform the stack-holders of the area about the state-of-the-art XML methods and encourage those to move from the ML to XML in transition to a NetZero future. This work has also highlighted the research gaps and potential future research directions for the battery community. Keywords: lithium–ion battery; machine learning; explainability; XML; interpretability; manufacturing processes; state of health; state of charge 1. Introduction Lithium–ion batteries (LiBs) have become the dominant technology for powering electric vehicles (EVs) and large-scale energy storage systems due to their high energy density, long cycle life, and relatively low cost. However, the complex nature of these batteries and the lack of understanding of their underlying electrochemical processes have made it difﬁcult to predict and control their

FAQs

What is the scope of explainable machine learning (XML) in this review?

The review covers XML for lithium–ion batteries both in manufacturing/production and during operation. It addresses structure and process optimization, as well as state estimation and control.

Which battery aspects are targeted for monitoring and control during use?

It focuses on monitoring states related to state of health, state of charge, and energy. These support control and improved reliability in battery systems.

Why is explainability important when applying machine learning to lithium–ion batteries?

The paper motivates XML as a way to make ML methods more transparent for battery stakeholders. It emphasizes a transition from ML toward XML to support progress in a NetZero future and to address research gaps.

Aug 5, 2026

Upload by Finn