Machine Learning in Lithium-Ion Battery Cell Production - A Comprehensive Mapping Study

Aug 3, 2026

Upload by Himbo

Battery cell production is central to sustainable electrification, yet its multi-step, parameter-rich processes still lack clear causality linking manufacturing and environment to final cell performance. This comprehensive mapping study systematically reviews state-of-the-art machine learning applications in lithium-ion battery cell production, summarizing product and process parameters and the algorithms used. Cross-perspective comparisons consolidate current capabilities and identify future research directions to further enable smart, sustainable battery manufacturing.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Motivation and sustainability impact

Battery value chain and process complexity

Data-driven approaches and research gap

Related Work (Background)

ML in battery materials and system-level operation

Prior reviews on data availability and manufacturing

Need for mapping ML applications in cell production

Batteries & Supercaps Review [doi.org/10.1002/batt.202300046](doi.org/10.1002/batt.202300046) [www.batteries-supercaps.org](www.batteries-supercaps.org) Machine Learning in Lithium-Ion Battery Cell Production: A Comprehensive Mapping Study Sajedeh Haghi,*[a] Marc Francis V. Hidalgo,[b, c] Mona Faraji Niri,[b, c] Rüdiger Daub,[a] and James Marco[b, c] Batteries & Supercaps 2023, e202300046 (1 of 14) © 2023 The Authors. Batteries & Supercaps published by Wiley-VCH GmbH Batteries & Supercaps Review [doi.org/10.1002/batt.202300046](doi.org/10.1002/batt.202300046) 25666223, 0, With the global quest for improved sustainability, partially realized through the electrification of the transport and energy sectors, battery cell production has gained ever-increasing attention. An in-depth understanding of battery production processes and their interdependence is crucial for accelerating the commercialization of material developments, for example, at the volume predicted to underpin future electric vehicle production. Over the last five years, machine learning approaches have shown significant promise in understanding and optimizing the battery production processes. Based on a systematic mapping study, this comprehensive review details the state-of-the-art applications of machine learning within the domain of lithium-ion battery cell production and highlights the fundamental aspects, such as product and process parameters and adopted algorithms. The compiled findings derived from multi-perspective comparisons demonstrate the current capabilities and reveal future research opportunities in this field to further accelerate sustainable battery production. 1. Introduction The lithium-ion battery (LIB) is taking on a prominent role in the transition to a more sustainable future by facilitating zeroemission mobility and revolutionizing the energy sector. LIB technology is still subject to continuous improvement to meet the industry’s rising demands in terms of performance, costs, and quality. [1] Efforts are being made to optimize the entire battery value chain, which consists of different stages from material to cell production, battery pack, and recycling. Battery cell production is a crucial part of the value chain, accounting for 46 % of value-creation and macroeconomic opportunities by 2030.[2] The production process chain consists of multiple interconnected process steps with a large number of parameters that can influence the final cell characteristics. Due to the complexity of the processes with manifold interdependencies, the causality between the manufacturing parameters, environmental conditions, and product performance of both the final cell and its constituent components is still mostly unknown. Fora cost-efficient quality-oriented optimization of the process chain, an in-depth understanding of the individual process steps, their interdependencies, and their impact on the cell properties is deemed to be absolutely imperative. [3] Given the high complexity of the process chain, along with advancementsin digitalization and information technology, data-driven approaches have gained attention in battery research over recent years.[4,5] [a] S. Haghi, Prof. Dr. R. Daub Institute for Machine Tools and Industrial Management Technical University of Munich Boltzmannstr. 15, Garching 85748 (Germany) E-mail: sajedeh.haghi@iwb.tum.de [b] Dr. M. F. V. Hidalgo, Prof. Dr. M. F. Niri, Prof. Dr. J. Marco Warwick Manufacturing Group University of Warwick CV4 7AL Coventry (UK) [c] Dr. M. F. V. Hidalgo, Prof. Dr. M. F. Niri, Prof. Dr. J. Marco The Faraday Institution Quad One Harwell Science and Innovation Campus, Didcot (UK) Supporting information for this article is available on the WWW under [https://doi.org/10.1002/batt.202300046](https://doi.org/10.1002/batt.202300046) © 2023 The Authors. Batteries & Supercaps published by Wiley-VCH GmbH. This is an open access article under the terms of the C

FAQs

Why is understanding lithium-ion battery cell production processes important?

Battery cell production is a crucial part of the battery value chain and strongly influences final cell characteristics. Its process steps are interconnected and influenced by many parameters, making detailed understanding essential for effective optimization.

What does the mapping study focus on?

The review focuses on state-of-the-art machine learning applications specifically within lithium-ion battery cell production. It highlights product and process parameters and the algorithms used.

What challenges and research opportunities are identified?

The document notes that causality between manufacturing parameters, environmental conditions, and performance is still mostly unknown. By compiling findings from multi-perspective comparisons, it reveals future research opportunities to further accelerate sustainable battery production.

Aug 3, 2026

Upload by Himbo