Cylindrical lithium battery surface defect detection system and method based on visual recognition

By using V-groove roller friction drive and multi-camera synchronous triggering, a distortion-free cylindrical surface unfolding pattern is generated, solving the problems of blind zone and low detection efficiency in cylindrical lithium battery detection, and realizing highly efficient and automated detection and sorting.

CN122400166APending Publication Date: 2026-07-17NORTH CHINA UNIV OF WATER RESOURCES & ELECTRIC POWER

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NORTH CHINA UNIV OF WATER RESOURCES & ELECTRIC POWER
Filing Date
2026-05-06
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies struggle to perform blind-zone-free, high-efficiency, and automated surface defect detection on the circumferential and end faces of cylindrical lithium batteries. Furthermore, the lack of deep coupling between the detection algorithm and the hardware acquisition path leads to low detection efficiency and inconsistent results.

Method used

Using V-groove roller friction drive and linear motor material feeding, the rollers are rotated synchronously by stepper motor control. Combined with multi-camera synchronous triggering and pixel strip stitching, a distortion-free cylindrical surface unfolding image is generated, and the entire battery pack is efficiently and automatically detected and sorted.

Benefits of technology

It achieves blind-zone-free, high-efficiency detection of cylindrical lithium battery surfaces, ensuring consistent test results and efficient operation of automated processes, thereby improving detection efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122400166A_ABST
    Figure CN122400166A_ABST
Patent Text Reader

Abstract

本发明公开了一种基于视觉识别的圆柱形锂电池表面缺陷检测系统及方法,属于锂电池表面缺陷检测技术领域。针对现有圆柱形锂电池检测难以实现圆周面无盲区成像、多相机采集时序错位、整盘来料与检测工序衔接不畅、检测模型与硬件采集路径耦合度低的问题,采用V形槽滚轮摩擦驱动被测电池同步旋转,控制器触发圆周面相机及双端面相机采集图像,提取对应固定旋转角度的像素条拼接生成圆柱面无畸变展开图,结合训练后的YOLOv8目标检测模型识别缺陷,配套盘式来料、单排检测、整盘分拣的自动化物流路径实现连续作业。本发明可实现圆柱形锂电池全表面无盲区、高效率检测,检测精度与稳定性优异,适用于锂电池批量生产的在线质检场景。
Need to check novelty before this filing date? Find Prior Art