A Review of Research Progress on Surface Defect Detection Methods for Battery Shells of New Energy Vehicles

Driven by the dual-carbon target strategy, the new energy vehicle industry has achieved large-scale and rapid development. As the core protective component of power batteries, the surface quality of battery shells directly determines the operational safety and reliability of batteries. However, defects such as scratches, pits, and cracks easily occur on battery shells during forming processes, including stamping and deep drawing. Traditional manual detection suffers from bottlenecks, such as high labor intensity, low detection efficiency, and high false detection rates, making it difficult to adapt to the large-scale and high-cycle production requirements of modern industry. Firstly, this study systematically elaborates the material system, preparation process, and defect formation mechanism of battery shells, and clarifies the coupling mechanisms of material properties, process parameters, and equipment and environmental conditions for defect evolution. Subsequently, it compares and analyzes the principles, advantages and disadvantages, and applicable scenarios of traditional machine-vision- and deep-learning-based detection technologies, and focuses on analyzing the application performance and optimization paths of single-stage and two-stage object detection algorithms in shell defect recognition. Furthermore, it addresses the core challenges of deep-learning-based battery shell defect detection technologies in data, algorithm deployment, detection dimensions, and other aspects, and proposes targeted optimization strategies. Finally, the development directions, such as system integration and online learning, are forecasted. This study can provide theoretical support and technical references for the intelligent manufacturing of battery shell stamping and forming, as well as for surface defect detection.