The production process of power batteries is complex, and machine vision functions such as positioning, guidance, recognition, and measurement are used from the stirring and coating in the front section, to the synthesis and winding (stacking) and liquid injection stage of the battery cells in the middle section, and then to the formation and packaging in the rear section.
This issue focuses on the application cases of visual inspection in sealing nail welding. First, let's understand the pre - and post process flow of sealing nail welding:
Sealing nail welding is an important process to achieve complete isolation between the inside of the battery and the external environment. After the production of the battery cell is completed, it will be encapsulated into the battery shell, and a liquid injection hole will be left above the shell for electrolyte injection. After injecting electrolyte, a rubber plug will be inserted and transported to the sealing nail welding station for final shell sealing.
However, during the process of liquid injection and transportation, the electrolyte will remain in the slot of the cover plate, and after being left to stand for a long time, crystals will form. When welding sealing nails, it is often easy to have solder joints, explosion, leakage, pinholes, and off center welding. Welding defects can greatly reduce the performance of power batteries and even lead to them being scrapped. The intervention of machine vision plays a crucial role in ensuring the quality of power batteries.
Huahan Weiye's self-developed machine vision inspection system includes 2D/2.5D/3D/AI visual inspection, which can create a comprehensive solution for the entire process of power batteries for customers in the lithium battery industry. It covers multiple process steps, including electrode segment, battery cell segment, module segment, electrode appearance inspection, battery cell top cover welding inspection, battery cell appearance inspection, module welding, and PACK assembly.
Due to the rich forms of welding defects in sealing nails, it is difficult to define their edges; The detection area moves frequently, and the defect location has randomness; Some minor defects mixed with welding ash or cleaning circles pose significant challenges to machine vision inspection.
(Original image display)
① Sealing nails: positioning, guiding pre welding, and full welding.
② Sealing nail welding quality: missed welding, reversed placement, cracks, missed covers, false welding, burst points, welding pits, holes, broken welds, etc; Welding position offset and weld width.
1) 2D welding guide for battery sealing nails
2) Sealing nail 3D-AI welding quality inspection
(Lighting diagram)
1) The sealing nail on the nail adopts InnoVision 2D visual software developed by Huahan Weiye, combined with customized hardware facilities. The contour or grayscale matching tool is used to perform initial positioning of the sealing nail hole, and the circle detection tool automatically follows the initial positioning correction. The circle fitting tool is used to locate the center coordinate of the sealing nail hole, and output this coordinate for welding guidance, with high accuracy and fast calculation speed; Scanning speed 50mm/s, over kill<0.1%, missed kill=0%, fast speed, positioning/detection accuracy: ± 0.05mm, detection time<0.5s, fast speed, can be shipped in bulk.
(Presentation of renderings)
2) The quality inspection of sealing nail welding adopts the AIDI Suite deep learning intelligent detection system developed by Huahan, with 3D-AI deep fusion and self-developed patented "filtering and noise removal" algorithm to remove interference and noise during the detection process. At the same time, the self-developed defect detection algorithm marks areas with high mutation and selects marked areas that meet the defect determination requirements (size and area) for accurate identification of defects. The scanning speed is 50mm/s, the missed kill rate is 0%, and the over kill rate is less than 0.5%. The speed is fast and can stably identify defects.
(Presentation of renderings)
Currently, 2D visual inspection is widely used in the field of power batteries. However, with the increasingly refined requirements of battery companies for detection accuracy, speed, image transmission, and defect analysis, 3D vision has become a supplement to 2D vision, relying on the depth information of physical space and low dependence on external environment, occupying a very important position.
Huahan Weiye provides flexible customization solutions and develops a cost-effective 2D+3D-AI overall solution based on the actual situation of customers. The aim is to create automated, digital, and intelligent production lines for customers, help lithium battery enterprises achieve precise quality control and project implementation, and maximize the value of customer equipment investment. Not only does it save a lot of costs, significantly improve production efficiency, but it also better controls production quality.
Moreover, the company has a self-developed underlying algorithm platform that can achieve optimization effects from the lowest level algorithms according to the actual needs of the project, meeting the requirements of project speed and accuracy. A machine vision system solution that integrates 2D/3D/AI in all aspects, achieving functions such as visual guidance, QR code recognition, character recognition, barcode recognition, product positioning, defect detection and classification, and multi image flow image coordination processing for workpieces.
The software system is easy to operate, and ordinary employees can get started after one training session; Short deployment and launch cycle, able to complete debugging as soon as possible; The company currently has a delivery team of over 100 people, which can meet stringent project time requirements. To ensure product stability and reliability, we provide 7 * 24-hour after-sales service.
Since its establishment, the company has won high recognition from customers with its professional and pragmatic service spirit. Currently, there are landing cases in industries such as 3C electronic manufacturing, new energy, semiconductors, warehousing and logistics.