The increasing demand for lithium-ion batteries (LiBs) in electric vehicles, renewable energy storage and consumer electronics necessitates a transition towards high-performance, cost-effective, and sustainable manufacturing. Traditional manufacturing methods rely heavily on empirical trial-and-error approaches, leading to inefficiencies such as process variability, material waste and increased production costs. Recent advancements in digitalization, particularly artificial intelligence (AI) driven digital twins, offer transformative solutions to these challenges. This review presents a systematic framework for integrating AI and digital twin technologies into battery manufacturing, emphasizing their role in predictive maintenance, quality control, and process optimization. Unlike existing reviews, which primarily focus on theoretical modelling, this work examines real-world industrial applications, discusses challenges in large-scale AI adoption, and provides a practical roadmap for implementation. Key contributions include an analysis of digital models, shadows and twins in optimizing battery manufacturing processes and defect detection. Additionally, we highlight the contributions of Raw Material Suppliers, Battery Manufacturers, Technology and Innovation Partners, Policymakers and Regulators, along with actionable plans in establishing a fully digitalized battery production ecosystem. By bridging conventional manufacturing with intelligent digital frameworks, this review outlines a path toward scalable, high-quality, and sustainable battery production.

As the electrification of the transport sector progresses, an abundance of lithium-ion batteries inside electric vehicles (EVs) will reach their end-of-life (EoL). The cells inside battery packs will age differently depending on multiple factors during their use. Currently, there is limited publicly available research on the degradation of the individual cells recovered from real-world EV usage. Once they have been recovered from the vehicle, large-format pouch cells are challenging to characterise, measure their internal structure and determine state-of-health (SoH). Here, large-format (261 x 216 x 7.91 mm) Nissan Leaf cells are harvested from an EV and four complementary non-destructive techniques are used to distinguish the ageing of cells arranged in varying orientations and locations within the pack. The measurement suite includes infrared thermography, ultrasonic mapping, X-ray computed tomography, and synchrotron X-ray diffraction, and represents a unique combination of characterisation techniques. We found that each of the non-destructive diagnostic techniques corroborated each other yet provide different complementary insights. The influence of orientation and location of the cells is significant, with the rotated/vertically aligned cells differing significantly from the flat/horizontally aligned cells in mode and degree of ageing. These insights provide new information on cell degradation that can help to influence pack design and illustrates how rapid and relatively inexpensive technology can provide sufficient information for practical assessment compared to costly synchrotron studies. Such an approach can inform decision support at EoL and more efficient battery production reducing the wastage of raw materials.

Lithium-ion batteries (LIBs) exhibit sudden non-linear degradation (known as the cell knee point) in operating use, but a quick, simple, and industrially applicable method of predicting knee point failure remains elusive. Addressing this gap, we show for the first time that the Warburg coefficient (readily obtainable from EIS measurement) can predict electrolyte-based knee point failure, well before extreme capacity degradation, in retired electric vehicle pouch cells. The technique is found to be effective across a wide range of battery states of charge (SOC), and the information can be extracted from the pouch cells in only 10 seconds. In principle this enables early detection of electrolyte-based knee point failure within commercial electric vehicle cells if applied ex situ through offline diagnosis (energy storage system) within second life battery application systems, thus allowing greater predictability with regard to the remaining lifetime of the battery.