一种基于深度学习的元器件引脚缺陷视觉在线检测系统
The deep learning-based online visual inspection system for component pin defects solves the problem of difficulty in identifying minute pin offset defects in existing technologies, achieving high-precision online inspection, improving inspection accuracy and stability, and is suitable for surface mount technology (SMT) production lines.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAMEN WEICHUANG INTELLIGENT TECH CO LTD
- Filing Date
- 2026-04-30
- Publication Date
- 2026-07-17
AI Technical Summary
Existing machine vision inspection technology has difficulty accurately identifying minute pin offset defects on surface mount technology (SMT) production lines, resulting in false positives and false negatives. It cannot meet the requirements for high-precision online inspection, mainly due to uneven reflection caused by spatial orientation deviations after chip mounting and flux residue.
A deep learning-based online visual inspection system for component pin defects is adopted. The system acquires images through an industrial camera and performs image enhancement processing. It then extracts pin mask images using a deep learning segmentation network, constructs a spatial reference plane and performs attitude correction, and finally obtains the inspection results through morphological processing and deviation calculation.
It achieves high-precision and robust online detection of component pin defects, reduces false detection and missed detection rates, improves detection accuracy and stability, adapts to the real-time detection needs of surface mount technology chip production lines, and ensures the soldering quality of printed circuit board chip pins.
Smart Images
Figure CN122115463B_ABST