Long-sequence voltage series forecasting for internal short circuit early detection of lithium-ion batteries

Summary: Accurate early detection of internal short circuits (ISCs) is indispensable for safe and reliable application of lithium-ion batteries (LiBs). However, the major challenge is finding a reliable standard to judge whether the battery suffers from ISCs. In this work, a deep learning approach with multi-head attention and a multi-scale hierarchical learning mechanism based on encoder-decoder architecture is developed to accurately forecast voltage and power series. By using the predicted voltage without ISCs as the standard and detecting the consistency of the collected and predicted voltage series, we develop a method to detect ISCs quickly and accurately. In this way, we achieve an average percentage accuracy of 86% on the dataset, including different batteries and the equivalent ISC resistance from 1,000 Ω to 10 Ω, indicating successful application of the ISC detection method. The bigger picture: Lithium-ion batteries are applied in many fields because of their high energy and power density. However, accidents associated with battery fires have raised great public awareness and concerns about safety issues. Internal short circuits (ISCs) are the main reason for battery fires. However, so far, there is still a lack of accurate and quick methods for ISC detection. To address this challenge, we report a method to predict future battery characteristics using deep learning. ISCs can be detected accurately and quickly by inconsistency of the evolution of normal and ISC battery characteristics. The method is demonstrated over the full life cycle of batteries. The general method can also be applied to fault detection of many other mechanical and electronic systems. The long-term goal of this research is to achieve a digital twin with broader applications for intelligent battery management, such as prolonging battery life and optimizing charging profiles.