3D AI AOI Equipment Detects Anode - Cathode Alignment Defects in New Energy Batteries

In the booming new energy battery industry, quality inspection is crucial. WeLinkirt's 3D AI AOI equipment provides a reliable solution for the detection of anode-cathode alignment in the winding/lamination process of new energy batteries with its advanced technology.

User Scenario: A leading new energy battery manufacturer, on its winding/lamination production line, mainly produces lithium-ion batteries. The detection object focuses on the alignment of the anode and cathode of the battery. This step plays a crucial role in the performance and safety of the battery. In the X-ray CT detection process, ensuring the precise alignment of the anode and cathode is an important procedure to guarantee the battery quality.

Pain Points: In traditional detection methods, there are many quantitative dilemmas. On the one hand, since the detection of anode-cathode alignment requires micron-level accuracy, traditional 2D optical detection has many blind spots, resulting in a miss-detection rate as high as 3%. This allows some unqualified products to enter subsequent processes, increasing the risk of product recalls and safety hazards. On the other hand, the false-alarm rate reaches 20%. Frequent false alarms not only increase the burden of manual re-inspection but also reduce production efficiency. In addition, as the application of domestic AI chips in industrial vision quality inspection has gradually become a hot topic, traditional equipment has difficulty meeting the requirements of intelligent manufacturing defect detection in terms of computing power and algorithm adaptability, and cannot achieve efficient and accurate detection.

Technical Principle

WeLinkirt's 3D AI AOI equipment uses self-developed 3D cameras and 3D morphology reconstruction/point cloud technology to solve the above problems. The self-developed 3D camera can capture the 3D image information of the battery's anode and cathode. Compared with traditional 2D cameras, it provides more depth information. Through 3D morphology reconstruction and point cloud technology, the information captured by the camera can be converted into an accurate 3D model. This process is effective because during the winding/lamination process, the alignment of the anode and cathode will cause subtle changes in their 3D morphology. These changes may be difficult to detect in 2D images but will be clearly shown in the 3D model. For example, alignment deviation will cause local height or angle changes. By analyzing the 3D point cloud data, these hidden defects can be accurately identified. In addition, the equipment also uses 2D-3D fusion technology, combining the texture information of 2D images and the depth information of 3D images to further improve the detection accuracy.

• The self-developed 3D camera obtains rich 3D image information, providing a detection basis in the depth dimension.
• 3D morphology reconstruction and point cloud technology convert image information into an analyzable 3D model, facilitating the discovery of subtle alignment defects.
• 2D-3D fusion technology combines the advantages of two types of image information to improve detection accuracy.

WeLinkirt's Solution and Product

Centered on the 3D AI AOI equipment, WeLinkirt provides a complete detection solution. The equipment has high-precision detection capabilities and can detect hidden solder joints, coplanarity, micron-level morphology, and pores and other defects in 2D optical blind spots. It is especially suitable for the detection of anode-cathode alignment in new energy batteries. During the implementation process, it can cooperate with the DaoAI AI AOI software system. Based on the feature recognition of the visual basic model, the software system can realize 0-code automatic programming for a good product in 5 minutes. Through APDT positive-sample/few-sample learning (only 1-20 good samples are needed) and combined with the semantic false-alarm filtering function, the detection process is further optimized, and the detection efficiency and accuracy are improved.

The 3D AI AOI equipment brings new breakthroughs to the quality inspection of new energy batteries with advanced technology.

Quantitative Results: After using WeLinkirt's 3D AI AOI equipment, the detection results are remarkable. The miss-detection rate has been reduced from the original 3% to <0.6%, effectively preventing unqualified products from entering the market. The false-alarm rate has been significantly reduced by -85%, reducing the workload of manual re-inspection and improving production efficiency. At the same time, the equipment change-over time has been shortened to 5min, meeting the needs of rapid product switching on the production line and improving the overall production flexibility.