Survey of Lithium-Ion Battery Anomaly Detection Methods in Electric Vehicles

Abstract

With the rapid popularization of electric vehicles, the safety and reliability of lithium-ion batteries, as their core power source, have become major concerns. Effective anomaly detection is crucial for ensuring the safe operation of lithium-ion batteries. This article presents a comprehensive review of the anomaly types and detection methods used in lithium-ion batteries for electric vehicles. We classify battery anomalies into energy efficiency and safety anomalies based on severity, detailing their external causes and internal mechanisms. Existing anomaly detection methods are categorized into four types: knowledge-based, model-based, statistics-based, and machine learning-based approaches. We analyze the advantages, limitations, and suitable scenarios for each method. Finally, we discuss the challenges and future prospects in battery anomaly detection, offering valuable insights for researchers. Through a systematic review and analysis, this article aims to provide theoretical support and references for anomaly detection research on lithium-ion batteries, promoting the advancement of anomaly detection technologies in lithium-ion batteries.