Cognex Deep Learning detects surface defects on a cylindrical EV battery
A cylinder battery’s metal case needs to be inspected for surface defects before it is wrapped in its vinyl coating. An inspection system must be able to tolerate normal variations and insignificant anomalies on the battery’s case while identifying any serious scratches. Because each defect varies slightly in size and shape, programming this inspection with traditional rules-based vision algorithms is inefficient. Additionally, the cylindrical shape of the battery sometimes renders as blurry and un-focused in images, complicating inspection.
Manufacturers searching for greater inspection accuracy per batch turn to Cognex Deep Learning, the first deep learning-based software optimized for factory automation. Cognex Deep Learning offers an effective inspection solution, combining a human’s ability to appreciate minor variations with the reliability, consistency, and speed of an automated system. Using Cognex Industrial Cameras (CIC), Cognex Deep Learning locates surface defects and anomalies on the sides, tops, and bottoms of cylinder batteries while ignoring irrelevant variations. Cognex Deep Learning successfully identifies only those battery cases which are damaged, increasing manufacturers’ inspection accuracy and decreasing waste.