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

Abstract

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.

Interdependencies in Electrode Manufacturing: A Comprehensive Study Based on Design Augmentation and Explainable Machine Learning

“…To yield deeper insights into the complex interdependencies in electrode manufacturing and transform the so‐called black box models to glass box models, [39] XML methods were employed. Considering the relatively large number of input features, [15] the study utilized Accumulated Local Effects (ALE) [40] and permutation feature importance, [41] as common XML methods recognized for their robustness and unbiased nature. Additionally, the SHapley Additive exPlanations (SHAP) [42] values were used to offer granular, instance‐level explanations.…”

“…In a comprehensive mapping study, Haghi et al. [15] provided an overview of the existing machine learning (ML) studies, including the analyzed processes, parameters, and adopted algorithms, and highlighted the areas that have been less explored. Most of the existing studies concentrate on single process steps.…”

“…Most of the existing studies concentrate on single process steps. This focus can hinder a holistic analysis encompassing the entire electrode manufacturing, thereby limiting a complete understanding of the interconnected steps and their cumulative effects [15] . While the coating process was identified as one of the most analyzed processes in the data‐driven studies, the drying process, particularly on the pilot scale, received limited attention [15] .…”

“…This focus can hinder a holistic analysis encompassing the entire electrode manufacturing, thereby limiting a complete understanding of the interconnected steps and their cumulative effects [15] . While the coating process was identified as one of the most analyzed processes in the data‐driven studies, the drying process, particularly on the pilot scale, received limited attention [15] . Additionally, a set of overarching topics have been identified that need to be addressed to accelerate the use of ML in battery cell production.…”

Impact of Formulation and Slurry Properties on Lithium‐ion Electrode Manufacturing

“…Detailed information on the challenges can be found in recent battery manufacturing roadmaps, [23] review articles [24,25] and mapping studies. [26] Investigating the impact of formulation and control variables on slurry and electrode characteristics through experimental methods is vital but challenging and costly, especially in large-scale manufacturing. Thus, modelling approaches are needed to overcome these limitations.…”