Work

Synthetic Data Generation for AI-Informed End-of-Line Testing for Lithium-Ion Battery Production

Year: 2025

Type: article

Abstract: Lithium-ion batteries are a key technology in supply chains for modern electric vehicles. The production of lithium-ion batteries is complex and can be prone to defects. As such, the detection of defective batteries at end-of-line is critical to ensure performance and safety for the consumer. Existing end-of-line testing relies heavily on electrical measurements for identifying defective cells. However, it is possible that not all pertinent information is encoded within the electrical measurements alone. Reversible expansion in lithium-ion cells is an indicator of lithiation within the cell, while irreversible expansion is a consequence of the ageing process, unexpected expansion may indicate the presence of undesirable defects.. By measuring expansion in addition to electrical measurements, we aim to make better and faster quality predictions during end-of-line testing, thereby facilitating the early detection of potential defects.. To make these predictions, we implement artificial intelligence algorithms to extract information from the measurements. The training of these networks requires large amounts of training data, which is expensive to produce. In this paper, we demonstrate a first order physical modelling approach for generating synthetic data to pretrain artificial intelligence algorithms that perform anomaly detection on lithium-ion battery cells at end-of-line. By pretraining the artificial intelligence network using synthetic data, we can leverage existing physical models to reduce the amount of training data required.

Source: World Electric Vehicle Journal

DOI: 10.3390/wevj16020075

Authors: Tessa Krause, Daniel Nusko, Johannes Rittmann, Luciana Pitta Bauermann, Moritz Kroll, Carlo Holly