3D AI AOI Equipment Detects Welding Defects of New Energy Battery Tabs

Under the new potential of industrial AI implementation, AI-AOI technology brings new possibilities for defect detection in industrial production. WeLinkirt's 3D AI AOI equipment plays an important role in the quality inspection of new energy battery tab welding.

User Scenario: A leading new energy battery manufacturer's tab welding production line. The main products are various new energy batteries. The detection object is the welding part of the battery tabs, with a focus on quality issues such as burrs and false welding that occur during the tab welding process. The quality of tab welding directly affects the performance and safety of the battery, so accurate detection is crucial.

Pain Points: Under the new potential of industrial AI implementation, traditional detection methods are difficult to meet the requirements of new energy battery tab welding quality inspection. Traditional detection methods have a high miss-detection rate. According to statistics, the miss-detection rate can reach about 5%, which means that a large number of batteries with potential quality problems may enter the market. At the same time, the false-alarm rate is also relatively high, about 15%, which not only increases the workload of manual re-inspection but also reduces production efficiency. In addition, manual detection has high labor costs and a long model-change time. Generally, it takes more than 30 minutes to change the model, which cannot meet the needs of rapid production. Moreover, in terms of compliance, traditional detection methods are difficult to ensure the consistency and accuracy of detection results, and cannot meet the increasingly strict industry standards.

Technical Principle

WeLinkirt's 3D AI AOI equipment uses a self-developed 3D camera for image acquisition. Through 3D morphology reconstruction and point-cloud technology, it can obtain accurate 3D information of the tab welding part. The principle is that defects such as burrs and false welding at the tab welding have unique morphological characteristics in 3D space. The self-developed 3D camera can capture these subtle feature differences and convert them into point-cloud data. Then, advanced algorithms are used to analyze the point-cloud data and compare it with the pre-set standard model.

• For burrs, they are manifested as protruding parts in the 3D morphology, which are significantly different from the normal welding surface. They can be accurately identified through the height and shape analysis of the point-cloud data.
• False welding is manifested as discontinuity and height differences in the welding part. The algorithm can judge the existence of false welding according to the distribution and characteristics of the point-cloud data.
• The equipment also uses 2D-3D fusion technology, combining the texture information of 2D images and the morphological information of 3D point-clouds to further improve the accuracy of detection and effectively detect defects such as hidden solder joints, coplanarity, micron-level morphology, and air holes in the 2D optical blind area.

WeLinkirt's Solution and Product

Centered on the 3D AI AOI equipment, WeLinkirt provides a complete solution for new energy battery tab welding quality inspection. The equipment has high-precision detection capabilities and can detect micron-level morphological changes. In the implementation, the DaoAI AI AOI software system is first used for programming. Based on the feature recognition of the visual basic model, this system can realize 0-code automatic programming in 5 minutes with only one good product, and uses APDT positive-sample/few-sample learning (only 1-20 good products are needed), greatly shortening the programming time and sample requirements. At the same time, the false-alarm rate is effectively reduced through the semantic false-alarm filtering function. In addition, the DaoAI World model, as a unified base, provides the capabilities of semantic understanding, cross-scene generalization, and continuous learning from production-line feedback. It supports SDK/API/Docker deployment and can achieve 100% local privatization to ensure that the data does not leave the factory.

The 3D AI AOI equipment provides reliable guarantee for new energy battery tab welding quality inspection with its advanced technology and powerful functions.

Quantitative Results: After using WeLinkirt's 3D AI AOI equipment, the detection effect has been significantly improved. The detection rate has reached 98.5%, and the miss-detection rate has been reduced to <1.5%, effectively preventing batteries with quality problems from entering the market. The false-alarm rate has been reduced by -70%, greatly reducing the workload of manual re-inspection. The model-change time has been shortened from more than 30 minutes to 5 minutes, improving production efficiency and meeting the production needs of rapid model change.