Advanced fault diagnosis in batteries: Insights into fault mechanisms, sensor fusion, and artificial intelligence

• Key battery faults and their complex underlying mechanisms are analyzed. • AI-based methods for battery fault diagnosis and prognostics are discussed. • Integration of Al with advanced sensing to improve fault diagnosis performance is explored. • Main challenges and future research directions in the field are identified. With the increasing demand for sustainable and clean energy, lithium-ion batteries have emerged as one of the most essential energy storage technologies. However, safety concerns have become a major bottleneck, significantly constraining their widespread deployment. This highlights the critical need for efficient fault diagnosis to ensure the safe and reliable operation of battery systems. In recent years, artificial intelligence (AI) techniques, in combination with advanced sensing technologies, have attracted growing attention for battery fault diagnosis and prognosis. Nevertheless, their full potential and broad applicability remain underexplored. This review provides a systematic analysis of the integration of AI methodologies with advanced sensors, emphasizing their capabilities for accurate fault detection and prediction, while also identifying key challenges and future research directions in this evolving field. The study begins by outlining common battery fault types and their underlying mechanisms, offering a foundational understanding of the associated complexities. It then introduces state-of-the-art AI techniques applied in fault diagnosis. Then, recent advances in combining AI with advanced sensing technologies for battery diagnostics are examined. Finally, the limitations of current approaches are discussed, and promising directions are proposed to facilitate the development of intelligent, scalable, and robust fault diagnosis frameworks for lithium-ion battery systems.