Because battery tabs conduct electricity, they are fundamental to a battery cell’s overall efficiency, safety, and longevity. This application focuses on battery tab inspection after the stamping process before they’re welded to electrodes.
.png)
What manufacturing defects occur?
Battery tabs are made from various metals which are thin, soft, and easily damaged. They can be damaged early on due to their fragility during manufacturing processes used to shape and cut the tabs, any surface treatments they undergo to improve conductivity, and during handling and storage before the tab welding process. Common defects include:
These defects can lead to a poor weld downstream, resulting in premature failures, decreased battery performance, and safety risks that can cause thermal runaways, fires, or explosions. And in electric vehicles, lithium-ion batteries are the most expensive parts, so recalls should be avoided at all costs.
It is crucial for manufacturers to implement rigorous quality control measures and inspection processes to detect and rectify these electrode tab issues upstream before battery cells continue on to additional cell assembly and finishing manufacturing processes. Adding inspection prior to welding will help prevent unnecessarily wasting resources further downstream.
However, battery tab defects are difficult to detect. Tabs are made of metal components with low contrast and reflective surfaces, making defects hard to see. Traditional machine vision systems struggle to capture clear images and distinguish between actual defects, reflective surfaces, and the background, ultimately missing defects or causing false rejections.
Battery tab defects manifest in various shapes, sizes, and locations. And as battery technology evolves, their manufacturing processes change. Traditional machine vision requires programming hundreds of hand-crafted rules, causing them to fail to detect new or variable defects that don’t match their programmed parameters and making them slow to adapt to changes.
The Solution
UnitX’s AI-powered inspection effectively detects battery tab defects where other solutions fail.
First, the OptiX imaging system illuminates and images battery tab surfaces. Then, the CorteX Central AI platform is trained on stamping defects. Lastly, those AI models are deployed to the CorteX Edge inference system to detect and classify defects in-line.
Why UnitX for battery tab stamping inspection?
OptiX provides superior images that minimize reflectivity while maximizing defect visibility. It has 32 independently controllable lighting sources that can be optimized for battery tab surfaces and defects via software. Its computational imaging capability can be used to take multiple shots and eliminate hotspots caused by highly reflective battery tab surfaces. And its lighting dome design supports a very acute incidence angle of projected light, causing even very tiny defects to cast shadows which increase their visibility.
CorteX accurately detects random, complex defects. It automatically normalizes for variability in positions and orientations and recognizes defects down to the pixel-level.
UnitX supports fast experimentation and adapts to changes in production environments. OptiX lighting is easily configured via software and CorteX AI models are sample efficient– they only require a few images to train on new defect types.
With UnitX, manufacturers automate battery tab inspection to:
- Prevent quality escapes that cause degraded battery performance and failure, safety risks, and costly recalls
- Minimize false rejection rates common with traditional machine vision, reducing scrap and wasted materials
- Replace manual inspectors, saving manufacturers money and improving efficiency
UnitX Inspection Example Deep Dive
In this example, we inspected battery cell tabs for structural defects like torn tabs that can occur during fabrication due to equipment calibration failures or process failures when cutting or shaping the tabs, or during handling of the tabs when arranging them for assembly.
Imaging
First, we used OptiX to capture images of the battery cell tabs, making sure we captured both defective and OK parts.
Training
Next, we used CorteX Central to train our models. We created a label for the primary defect we want to detect, torn tabs.
We then labeled those defects in the images we captured from OptiX, using just a few images of the torn tab defect.
Detection
Next, we deployed the AI models to CorteX Edge on new cells, resulting in the accurate detection and classification of torn tabs.
